1 |
8.00 |
Optimal Strategies Against Generative Attacks |
8 8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Sparse Coding With Gated Learned Ista |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Dynamics-aware Unsupervised Skill Discovery |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Cater: A Diagnostic Dataset For Compositional Actions & Temporal Reasoning |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Learning To Balance: Bayesian Meta-learning For Imbalanced And Out-of-distribution Tasks |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
A Generalized Training Approach For Multiagent Learning |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Contrastive Learning Of Structured World Models |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Enhancing Adversarial Defense By K-winners-take-all |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Backpack: Packing More Into Backprop |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Principled Weight Initialization For Hypernetworks |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Understanding And Robustifying Differentiable Architecture Search |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Restricting The Flow: Information Bottlenecks For Attribution |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Implementation Matters In Deep Rl: A Case Study On Ppo And Trpo |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Nas-bench-102: Extending The Scope Of Reproducible Neural Architecture Search |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Mathematical Reasoning In Latent Space |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Mirror-generative Neural Machine Translation |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Rotation-invariant Clustering Of Functional Cell Types In Primary Visual Cortex |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
On The “steerability” Of Generative Adversarial Networks |
8 8 8 |
0.00 |
Accept (Poster) |
1 |
8.00 |
The Logical Expressiveness Of Graph Neural Networks |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Meta-learning With Warped Gradient Descent |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Differentiable Reasoning Over A Virtual Knowledge Base |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Differentiation Of Blackbox Combinatorial Solvers |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Geometric Analysis Of Nonconvex Optimization Landscapes For Overcomplete Learning |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Simplified Action Decoder For Deep Multi-agent Reinforcement Learning |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Gendice: Generalized Offline Estimation Of Stationary Values |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Data-dependent Gaussian Prior Objective For Language Generation |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Causal Discovery With Reinforcement Learning |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
How Much Position Information Do Convolutional Neural Networks Encode? |
8 8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Why Gradient Clipping Accelerates Training: A Theoretical Justification For Adaptivity |
8 8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
A Theory Of Usable Information Under Computational Constraints |
8 8 |
0.00 |
Accept (Talk) |
1 |
8.00 |
Freelb: Enhanced Adversarial Training For Language Understanding |
8 8 |
0.00 |
Accept (Spotlight) |
1 |
8.00 |
Hyper-sagnn: A Self-attention Based Graph Neural Network For Hypergraphs |
8 8 |
0.00 |
Accept (Poster) |
1 |
8.00 |
Smooth Markets: A Basic Mechanism For Organizing Gradient-based Learners |
8 8 |
0.00 |
Accept (Poster) |
1 |
8.00 |
Depth-width Trade-offs For Relu Networks Via Sharkovsky’s Theorem |
8 8 |
0.00 |
Accept (Spotlight) |
2 |
7.50 |
Vq-wav2vec: Self-supervised Learning Of Discrete Speech Representations |
8 6 8 8 |
0.75 |
Accept (Poster) |
2 |
7.50 |
Rna Secondary Structure Prediction By Learning Unrolled Algorithms |
8 8 8 6 |
0.75 |
Accept (Talk) |
3 |
7.33 |
Is A Good Representation Sufficient For Sample Efficient Reinforcement Learning? |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Adversarial Training And Provable Defenses: Bridging The Gap |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Low-resource Knowledge-grounded Dialogue Generation |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Truth Or Backpropaganda? An Empirical Investigation Of Deep Learning Theory |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Directional Message Passing For Molecular Graphs |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Reformer: The Efficient Transformer |
8 8 6 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Cross-lingual Alignment Vs Joint Training: A Comparative Study And A Simple Unified Framework |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
What Graph Neural Networks Cannot Learn: Depth Vs Width |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Assemblenet: Searching For Multi-stream Neural Connectivity In Video Architectures |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Compressive Transformers For Long-range Sequence Modelling |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
At Stability’s Edge: How To Adjust Hyperparameters To Preserve Minima Selection In Asynchronous Training Of Neural Networks? |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Comparing Fine-tuning And Rewinding In Neural Network Pruning |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Mogrifier Lstm |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Graphzoom: A Multi-level Spectral Approach For Accurate And Scalable Graph Embedding |
8 8 6 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Reconstructing Continuous Distributions Of 3d Protein Structure From Cryo-em Images |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Neural Network Branching For Neural Network Verification |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Online And Stochastic Optimization Beyond Lipschitz Continuity: A Riemannian Approach |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Polylogarithmic Width Suffices For Gradient Descent To Achieve Arbitrarily Small Test Error With Shallow Relu Networks |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Deep Network Classification By Scattering And Homotopy Dictionary Learning |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Meta-learning Without Memorization |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Harnessing Structures For Value-based Planning And Reinforcement Learning |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Unbiased Contrastive Divergence Algorithm For Training Energy-based Latent Variable Models |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Disentangling Neural Mechanisms For Perceptual Grouping |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Mixed-curvature Variational Autoencoders |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Symplectic Ode-net: Learning Hamiltonian Dynamics With Control |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Deep Batch Active Learning By Diverse, Uncertain Gradient Lower Bounds |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Deep Imitative Models For Flexible Inference, Planning, And Control |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Cyclical Stochastic Gradient Mcmc For Bayesian Deep Learning |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Scaling Autoregressive Video Models |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
A Mutual Information Maximization Perspective Of Language Representation Learning |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Ddsp: Differentiable Digital Signal Processing |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
On Mutual Information Maximization For Representation Learning |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Observational Overfitting In Reinforcement Learning |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Federated Learning With Matched Averaging |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Latent Normalizing Flows For Many-to-many Cross Domain Mappings |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Convolutional Conditional Neural Processes |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Meta-q-learning |
8 8 6 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Measuring The Reliability Of Reinforcement Learning Algorithms |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Physics-aware Difference Graph Networks For Sparsely-observed Dynamics |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Learning Hierarchical Discrete Linguistic Units From Visually-grounded Speech |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Symplectic Recurrent Neural Networks |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
End To End Trainable Active Contours Via Differentiable Rendering |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
What Can Neural Networks Reason About? |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Discriminative Particle Filter Reinforcement Learning For Complex Partial Observations |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Thieves On Sesame Street! Model Extraction Of Bert-based Apis |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
High Fidelity Speech Synthesis With Adversarial Networks |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Disagreement-regularized Imitation Learning |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Stable Rank Normalization For Improved Generalization In Neural Networks And Gans |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Doubly Robust Bias Reduction In Infinite Horizon Off-policy Estimation |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Fasterseg: Searching For Faster Real-time Semantic Segmentation |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Robust Subspace Recovery Layer For Unsupervised Anomaly Detection |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Seed Rl: Scalable And Efficient Deep-rl With Accelerated Central Inference |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
On The Equivalence Between Node Embeddings And Structural Graph Representations |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Harnessing The Power Of Infinitely Wide Deep Nets On Small-data Tasks |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
The Ingredients Of Real World Robotic Reinforcement Learning |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Watch The Unobserved: A Simple Approach To Parallelizing Monte Carlo Tree Search |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Meta-learning Acquisition Functions For Transfer Learning In Bayesian Optimization |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
On The Convergence Of Fedavg On Non-iid Data |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Classification-based Anomaly Detection For General Data |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Learning Robust Representations Via Multi-view Information Bottleneck |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Poly-encoders: Architectures And Pre-training Strategies For Fast And Accurate Multi-sentence Scoring |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Your Classifier Is Secretly An Energy Based Model And You Should Treat It Like One |
6 8 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Deep Learning For Symbolic Mathematics |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Progressive Learning And Disentanglement Of Hierarchical Representations |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Energy-based Models For Atomic-resolution Protein Conformations |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Lambdanet: Probabilistic Type Inference Using Graph Neural Networks |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Sumo: Unbiased Estimation Of Log Marginal Probability For Latent Variable Models |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Glad: Learning Sparse Graph Recovery |
8 6 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Program Guided Agent |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Graph Neural Networks Exponentially Lose Expressive Power For Node Classification |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
A Closer Look At Deep Policy Gradients |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Fast Task Inference With Variational Intrinsic Successor Features |
8 6 8 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Generalization Of Two-layer Neural Networks: An Asymptotic Viewpoint |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Electra: Pre-training Text Encoders As Discriminators Rather Than Generators |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Network Deconvolution |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Intensity-free Learning Of Temporal Point Processes |
8 6 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Fspool: Learning Set Representations With Featurewise Sort Pooling |
8 8 6 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Massively Multilingual Sparse Word Representations |
6 8 8 |
0.89 |
Accept (Poster) |
3 |
7.33 |
Finite Depth And Width Corrections To The Neural Tangent Kernel |
6 8 8 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Gradient Descent Maximizes The Margin Of Homogeneous Neural Networks |
8 8 6 |
0.89 |
Accept (Talk) |
3 |
7.33 |
Sequential Latent Knowledge Selection For Knowledge-grounded Dialogue |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Learning To Plan In High Dimensions Via Neural Exploration-exploitation Trees |
8 8 6 |
0.89 |
Accept (Spotlight) |
3 |
7.33 |
Albert: A Lite Bert For Self-supervised Learning Of Language Representations |
8 8 6 |
0.89 |
Accept (Spotlight) |
4 |
7.00 |
An Exponential Learning Rate Schedule For Batch Normalized Networks |
8 8 6 6 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Encoding Word Order In Complex Embeddings |
8 6 8 6 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
And The Bit Goes Down: Revisiting The Quantization Of Neural Networks |
8 6 8 6 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Quantum Algorithms For Deep Convolutional Neural Networks |
6 8 8 6 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Target-embedding Autoencoders For Supervised Representation Learning |
6 8 6 8 |
1.00 |
Accept (Talk) |
4 |
7.00 |
Dream To Control: Learning Behaviors By Latent Imagination |
8 6 6 8 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Memo: A Deep Network For Flexible Combination Of Episodic Memories |
6 8 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Explanation By Progressive Exaggeration |
6 8 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Ridge Regression: Structure, Cross-validation, And Sketching |
6 8 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Double Neural Counterfactual Regret Minimization |
8 6 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Biologically Inspired Sleep Algorithm For Increased Generalization And Adversarial Robustness In Deep Neural Networks |
6 8 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Spectral Embedding Of Regularized Block Models |
8 6 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
How The Choice Of Activation Affects Training Of Overparametrized Neural Nets |
6 8 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Understanding L4-based Dictionary Learning: Interpretation, Stability, And Robustness |
8 6 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Neural Tangent Kernels, Transportation Mappings, And Universal Approximation |
8 6 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Sliced Cramer Synaptic Consolidation For Preserving Deeply Learned Representations |
6 8 |
1.00 |
Accept (Spotlight) |
4 |
7.00 |
Language Gans Falling Short |
6 8 |
1.00 |
Accept (Poster) |
4 |
7.00 |
Building Deep Equivariant Capsule Networks |
8 6 |
1.00 |
Accept (Talk) |
5 |
6.75 |
An Inductive Bias For Distances: Neural Nets That Respect The Triangle Inequality |
8 8 3 8 |
4.69 |
Accept (Poster) |
6 |
6.67 |
Disentanglement Through Nonlinear Ica With General Incompressible-flow Networks (gin) |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Fooling Detection Alone Is Not Enough: Adversarial Attack Against Multiple Object Tracking |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
In Search For A Sat-friendly Binarized Neural Network Architecture |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Dba: Distributed Backdoor Attacks Against Federated Learning |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Genesis: Generative Scene Inference And Sampling With Object-centric Latent Representations |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Measuring Compositional Generalization: A Comprehensive Method On Realistic Data |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Lagrangian Fluid Simulation With Continuous Convolutions |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Making Efficient Use Of Demonstrations To Solve Hard Exploration Problems |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Intrinsic Motivation For Encouraging Synergistic Behavior |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
On Robustness Of Neural Ordinary Differential Equations |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
On Identifiability In Transformers |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Estimating Gradients For Discrete Random Variables By Sampling Without Replacement |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Gradient-based Neural Dag Learning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Incremental Rnn: A Dynamical View. |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Deep Double Descent: Where Bigger Models And More Data Hurt |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning To Retrieve Reasoning Paths Over Wikipedia Graph For Question Answering |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Simple And Effective Regularization Methods For Training On Noisily Labeled Data With Generalization Guarantee |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Sqil: Imitation Learning Via Reinforcement Learning With Sparse Rewards |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Reinforcement Learning With Competitive Ensembles Of Information-constrained Primitives |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Neural Outlier Rejection For Self-supervised Keypoint Learning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Rényi Fair Inference |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
U-gat-it: Unsupervised Generative Attentional Networks With Adaptive Layer-instance Normalization For Image-to-image Translation |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Multi-agent Interactions Modeling With Correlated Policies |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Decoupling Representation And Classifier For Long-tailed Recognition |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Estimating Counterfactual Treatment Outcomes Over Time Through Adversarially Balanced Representations |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Neural Symbolic Reader: Scalable Integration Of Distributed And Symbolic Representations For Reading Comprehension |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Inductive Representation Learning On Temporal Graphs |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Training Generative Adversarial Networks From Incomplete Observations Using Factorised Discriminators |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Denoising And Regularization Via Exploiting The Structural Bias Of Convolutional Generators |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Controlling Generative Models With Continuous Factors Of Variations |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Intrinsically Motivated Discovery Of Diverse Patterns In Self-organizing Systems |
6 6 8 |
0.89 |
Accept (Talk) |
6 |
6.67 |
Influence-based Multi-agent Exploration |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Asymptotics Of Wide Networks From Feynman Diagrams |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Provable Robustness Against All Adversarial -perturbations For |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
From Variational To Deterministic Autoencoders |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Probabilistic Formulation Of Unsupervised Text Style Transfer |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Black-box Adversarial Attack With Transferable Model-based Embedding |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Discrepancy Ratio: Evaluating Model Performance When Even Experts Disagree On The Truth |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Pitfalls Of In-domain Uncertainty Estimation And Ensembling In Deep Learning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning The Arrow Of Time For Problems In Reinforcement Learning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Transformer-xh: Multi-hop Question Answering With Extra Hop Attention |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learned Step Size Quantization |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Mutual Mean-teaching: Pseudo Label Refinery For Unsupervised Domain Adaptation On Person Re-identification |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Ensemble Distribution Distillation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Drawing Early-bird Tickets: Toward More Efficient Training Of Deep Networks |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Detecting And Diagnosing Adversarial Images With Class-conditional Capsule Reconstructions |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Order Learning And Its Application To Age Estimation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Inductive Matrix Completion Based On Graph Neural Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Posterior Sampling For Multi-agent Reinforcement Learning: Solving Extensive Games With Imperfect Information |
6 6 8 |
0.89 |
Accept (Talk) |
6 |
6.67 |
Intriguing Properties Of Adversarial Training At Scale |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Efficient Transformer For Mobile Applications |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Reducing Transformer Depth On Demand With Structured Dropout |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Theoretical Analysis Of The Number Of Shots In Few-shot Learning |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning Representations For Binary-classification Without Backpropagation |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Fsnet: Compression Of Deep Convolutional Neural Networks By Filter Summary |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Amrl: Aggregated Memory For Reinforcement Learning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
The Function Of Contextual Illusions |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Neural Machine Translation With Universal Visual Representation |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Information Geometry Of Orthogonal Initializations And Training |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Batch-shaping For Learning Conditional Channel Gated Networks |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Multi-scale Representation Learning For Spatial Feature Distributions Using Grid Cells |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Query-efficient Meta Attack To Deep Neural Networks |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Fair Comparison Of Graph Neural Networks For Graph Classification |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Breaking Certified Defenses: Semantic Adversarial Examples With Spoofed Robustness Certificates |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Monotonic Multihead Attention |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Continual Learning With Hypernetworks |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Decoding As Dynamic Programming For Recurrent Autoregressive Models |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Diverse Trajectory Forecasting With Determinantal Point Processes |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Co-attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-occurring In Data |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Multiplicative Interactions And Where To Find Them |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
You Can Teach An Old Dog New Tricks! On Training Knowledge Graph Embeddings |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Deepsphere: A Graph-based Spherical Cnn |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Learning To Control Pdes With Differentiable Physics |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Emergence Of Functional And Structural Properties Of The Head Direction System By Optimization Of Recurrent Neural Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Model Based Reinforcement Learning For Atari |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Dynamically Pruned Message Passing Networks For Large-scale Knowledge Graph Reasoning |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Mixout: Effective Regularization To Finetune Large-scale Pretrained Language Models |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
On The Geometry And Learning Low-dimensional Embeddings For Directed Graphs |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
The Break-even Point On The Optimization Trajectories Of Deep Neural Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Understanding And Improving Information Transfer In Multi-task Learning |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Abductive Commonsense Reasoning |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Tree-structured Attention With Hierarchical Accumulation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Pay Attention To Features, Transfer Learn Faster Cnns |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Gradientless Descent: High-dimensional Zeroth-order Optimization |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Knowledge Consistency Between Neural Networks And Beyond |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning From Rules Generalizing Labeled Exemplars |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Variational Recurrent Models For Solving Partially Observable Control Tasks |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics For Neural Sequence Models |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Tranquil Clouds: Neural Networks For Learning Temporally Coherent Features In Point Clouds |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Spike-based Causal Inference For Weight Alignment |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Sample Efficient Policy Gradient Methods With Recursive Variance Reduction |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Exploring Model-based Planning With Policy Networks |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Variational Autoencoders For Highly Multivariate Spatial Point Processes Intensities |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Kernelized Wasserstein Natural Gradient |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Can Gradient Clipping Mitigate Label Noise? |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Rethinking The Security Of Skip Connections In Resnet-like Neural Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Reinforcement Learning Based Graph-to-sequence Model For Natural Question Generation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Deep Neuroethology Of A Virtual Rodent |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Pretrained Encyclopedia: Weakly Supervised Knowledge-pretrained Language Model |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
N-beats: Neural Basis Expansion Analysis For Interpretable Time Series Forecasting |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Uncertainty-guided Continual Learning With Bayesian Neural Networks |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Toward Amortized Ranking-critical Training For Collaborative Filtering |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Revisiting Self-training For Neural Sequence Generation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Neural Dirichlet Process Mixture Model For Task-free Continual Learning |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Ride: Rewarding Impact-driven Exploration For Procedurally-generated Environments |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Neurquri: Neural Question Requirement Inspector For Answerability Prediction In Machine Reading Comprehension |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Actor-critic Provably Finds Nash Equilibria Of Linear-quadratic Mean-field Games |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Lipschitz Constant Estimation For Neural Networks Via Sparse Polynomial Optimization |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Latent Morphology Model For Open-vocabulary Neural Machine Translation |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Are Pre-trained Language Models Aware Of Phrases? Simple But Strong Baselines For Grammar Induction |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Padé Activation Units: End-to-end Learning Of Flexible Activation Functions In Deep Networks |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Improving Adversarial Robustness Requires Revisiting Misclassified Examples |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning Expensive Coordination: An Event-based Deep Rl Approach |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Scalable Model Compression By Entropy Penalized Reparameterization |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Permutation Equivariant Models For Compositional Generalization In Language |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Evolutionary Population Curriculum For Scaling Multi-agent Reinforcement Learning |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
On The Interaction Between Supervision And Self-play In Emergent Communication |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Locality And Compositionality In Zero-shot Learning |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Distributed Bandit Learning: Near-optimal Regret With Efficient Communication |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Fast Is Better Than Free: Revisiting Adversarial Training |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Towards Stabilizing Batch Statistics In Backward Propagation Of Batch Normalization |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Extreme Tensoring For Low-memory Preconditioning |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Scale-equivariant Steerable Networks |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Query2box: Reasoning Over Knowledge Graphs In Vector Space Using Box Embeddings |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Consistency Regularization For Generative Adversarial Networks |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Making Sense Of Reinforcement Learning And Probabilistic Inference |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Reclor: A Reading Comprehension Dataset Requiring Logical Reasoning |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Semi-supervised Generative Modeling For Controllable Speech Synthesis |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
The Intriguing Role Of Module Criticality In The Generalization Of Deep Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Training Individually Fair Ml Models With Sensitive Subspace Robustness |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Tabfact: A Large-scale Dataset For Table-based Fact Verification |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Snode: Spectral Discretization Of Neural Odes For System Identification |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Clevrer: Collision Events For Video Representation And Reasoning |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Never Give Up: Learning Directed Exploration Strategies |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Robust Reinforcement Learning For Continuous Control With Model Misspecification |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Neural Module Networks For Reasoning Over Text |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Sign Bits Are All You Need For Black-box Attacks |
8 6 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Learning To Learn By Zeroth-order Oracle |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Synthesizing Programmatic Policies That Inductively Generalize |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Hamiltonian Generative Networks |
8 6 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Prediction, Consistency, Curvature: Representation Learning For Locally-linear Control |
6 8 6 |
0.89 |
Accept (Poster) |
6 |
6.67 |
A Function Space View Of Bounded Norm Infinite Width Relu Nets: The Multivariate Case |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Hilloc: Lossless Image Compression With Hierarchical Latent Variable Models |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Geom-gcn: Geometric Graph Convolutional Networks |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Adaptive Correlated Monte Carlo For Contextual Categorical Sequence Generation |
6 6 8 |
0.89 |
Accept (Poster) |
6 |
6.67 |
Pc-darts: Partial Channel Connections For Memory-efficient Architecture Search |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Improving Generalization In Meta Reinforcement Learning Using Neural Objectives |
6 6 8 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Compression Based Bound For Non-compressed Network: Unified Generalization Error Analysis Of Large Compressible Deep Neural Network |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Hoppity: Learning Graph Transformations To Detect And Fix Bugs In Programs |
6 8 6 |
0.89 |
Accept (Spotlight) |
6 |
6.67 |
Real Or Not Real, That Is The Question |
8 6 6 |
0.89 |
Accept (Spotlight) |
7 |
6.50 |
A Closer Look At The Approximation Capabilities Of Neural Networks |
8 6 6 6 |
0.75 |
Accept (Poster) |
7 |
6.50 |
Quantifying Point-prediction Uncertainty In Neural Networks Via Residual Estimation With An I/o Kernel |
6 6 8 6 |
0.75 |
Accept (Poster) |
7 |
6.50 |
Learning Compositional Koopman Operators For Model-based Control |
6 6 6 8 |
0.75 |
Accept (Spotlight) |
7 |
6.50 |
Learning To Guide Random Search |
8 6 6 6 |
0.75 |
Accept (Poster) |
7 |
6.50 |
Dynamic Time Lag Regression: Predicting What & When |
8 6 6 6 |
0.75 |
Accept (Poster) |
7 |
6.50 |
Deepv2d: Video To Depth With Differentiable Structure From Motion |
6 6 6 8 |
0.75 |
Accept (Poster) |
7 |
6.50 |
Rethinking Softmax Cross-entropy Loss For Adversarial Robustness |
8 6 6 6 |
0.75 |
Accept (Poster) |
8 |
6.33 |
Understanding Knowledge Distillation In Non-autoregressive Machine Translation |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Self-labelling Via Simultaneous Clustering And Representation Learning |
8 3 8 |
5.56 |
Accept (Spotlight) |
8 |
6.33 |
Self-adversarial Learning With Comparative Discrimination For Text Generation |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Defending Against Physically Realizable Attacks On Image Classification |
3 8 8 |
5.56 |
Accept (Spotlight) |
8 |
6.33 |
Lazy-cfr: Fast And Near-optimal Regret Minimization For Extensive Games With Imperfect Information |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Variational Template Machine For Data-to-text Generation |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Word2ket: Space-efficient Word Embeddings Inspired By Quantum Entanglement |
3 8 8 |
5.56 |
Accept (Spotlight) |
8 |
6.33 |
Rapid Learning Or Feature Reuse? Towards Understanding The Effectiveness Of Maml |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Learning Disentangled Representations For Counterfactual Regression |
8 8 3 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Accelerating Sgd With Momentum For Over-parameterized Learning |
8 8 3 |
5.56 |
Accept (Poster) |
8 |
6.33 |
A Meta-transfer Objective For Learning To Disentangle Causal Mechanisms |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Learning From Explanations With Neural Module Execution Tree |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Fantastic Generalization Measures And Where To Find Them |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Guiding Program Synthesis By Learning To Generate Examples |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Single Episode Transfer For Differing Environmental Dynamics In Reinforcement Learning |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Triple Wins: Boosting Accuracy, Robustness And Efficiency Together By Enabling Input-adaptive Inference |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Coherent Gradients: An Approach To Understanding Generalization In Gradient Descent-based Optimization |
8 8 3 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Learning-augmented Data Stream Algorithms |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Weakly Supervised Disentanglement With Guarantees |
8 8 3 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Transferable Perturbations Of Deep Feature Distributions |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Measuring And Improving The Use Of Graph Information In Graph Neural Networks |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Automated Relational Meta-learning |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Minimizing Flops To Learn Efficient Sparse Representations |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Snow: Subscribing To Knowledge Via Channel Pooling For Transfer & Lifelong Learning |
8 8 3 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Decentralized Distributed Ppo: Mastering Pointgoal Navigation |
3 8 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Augmix: A Simple Data Processing Method To Improve Robustness And Uncertainty |
8 3 8 |
5.56 |
Accept (Poster) |
8 |
6.33 |
Counterfactuals Uncover The Modular Structure Of Deep Generative Models |
8 3 8 |
5.56 |
Accept (Poster) |
9 |
6.25 |
Improved Sample Complexities For Deep Neural Networks And Robust Classification Via An All-layer Margin |
6 8 8 3 |
4.19 |
Accept (Poster) |
9 |
6.25 |
Geometric Insights Into The Convergence Of Nonlinear Td Learning |
8 3 6 8 |
4.19 |
Accept (Poster) |
9 |
6.25 |
Dynamics-aware Embeddings |
3 8 6 8 |
4.19 |
Accept (Poster) |
10 |
6.20 |
Reanalysis Of Variance Reduced Temporal Difference Learning |
8 8 6 3 6 |
3.36 |
Accept (Poster) |
11 |
6.00 |
Meta-learning Deep Energy-based Memory Models |
6 6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Memory-based Graph Networks |
6 6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Training Binary Neural Networks With Real-to-binary Convolutions |
6 6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Lookahead: A Far-sighted Alternative Of Magnitude-based Pruning |
6 6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Q-learning With Ucb Exploration Is Sample Efficient For Infinite-horizon Mdp |
6 6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On The Variance Of The Adaptive Learning Rate And Beyond |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Emergent Systematic Generalization In A Situated Agent |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Quantifying The Cost Of Reliable Photo Authentication Via High-performance Learned Lossy Representations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Automated Curriculum Generation Through Setter-solver Interactions |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Optimistic Exploration Even With A Pessimistic Initialisation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Multi-agent Reinforcement Learning For Networked System Control |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Physics-as-inverse-graphics: Unsupervised Physical Parameter Estimation From Video |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On Solving Minimax Optimization Locally: A Follow-the-ridge Approach |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Learning-based Iterative Method For Solving Vehicle Routing Problems |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deephoyer: Learning Sparser Neural Network With Differentiable Scale-invariant Sparsity Measures |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Probabilistic Connection Importance Inference And Lossless Compression Of Deep Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Precision Gating: Improving Neural Network Efficiency With Dynamic Dual-precision Activations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Learning To Link |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Remixmatch: Semi-supervised Learning With Distribution Matching And Augmentation Anchoring |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Differentially Private Meta-learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Fast Neural Network Adaptation Via Parameters Remapping |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Sharing Knowledge In Multi-task Deep Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Rtfm: Generalising To New Environment Dynamics Via Reading |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Strategies For Pre-training Graph Neural Networks |
6 6 6 |
0.00 |
Accept (Spotlight) |
11 |
6.00 |
Adversarial Lipschitz Regularization |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Meta Reinforcement Learning With Autonomous Inference Of Subtask Dependencies |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deformable Kernels: Adapting Effective Receptive Fields For Object Deformation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Incorporating Bert Into Neural Machine Translation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Distance-based Learning From Errors For Confidence Calibration |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Dividemix: Learning With Noisy Labels As Semi-supervised Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Projection Based Constrained Policy Optimization |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Adversarial Policies: Attacking Deep Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
One-shot Pruning Of Recurrent Neural Networks By Jacobian Spectrum Evaluation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Sampling-free Learning Of Bayesian Quantized Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Understanding Generalization In Recurrent Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Graph Constrained Reinforcement Learning For Natural Language Action Spaces |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Spikegrad: An Ann-equivalent Computation Model For Implementing Backpropagation With Spikes |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Extracting And Leveraging Feature Interaction Interpretations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Gradient Regularization For Quantization Robustness |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Masked Based Unsupervised Content Transfer |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Framework For Robustness Certification Of Smoothed Classifiers Using F-divergences |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
V-mpo: On-policy Maximum A Posteriori Policy Optimization For Discrete And Continuous Control |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Mixed Precision Dnns: All You Need Is A Good Parametrization |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Thinking While Moving: Deep Reinforcement Learning With Concurrent Control |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Don’t Use Large Mini-batches, Use Local Sgd |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Keep Doing What Worked: Behavior Modelling Priors For Offline Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Imitation Learning Via Off-policy Distribution Matching |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Empirical Bayes Transductive Meta-learning With Synthetic Gradients |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On The Relationship Between Self-attention And Convolutional Layers |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Closer Look At The Optimization Landscapes Of Generative Adversarial Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Unsupervised Clustering Using Pseudo-semi-supervised Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Adversarial Autoaugment |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Dynamic Model Pruning With Feedback |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Understanding The Limitations Of Variational Mutual Information Estimators |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deep Semi-supervised Anomaly Detection |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Graph Convolutional Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Understanding The Limitations Of Conditional Generative Models |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Scalable Neural Methods For Reasoning With A Symbolic Knowledge Base |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Graphaf: A Flow-based Autoregressive Model For Molecular Graph Generation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Evaluating The Search Phase Of Neural Architecture Search |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Adversarial Example Detection And Classification With Asymmetrical Adversarial Training |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Adaptive Structural Fingerprints For Graph Attention Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On Universal Equivariant Set Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Option Discovery Using Deep Skill Chaining |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Unpaired Point Cloud Completion On Real Scans Using Adversarial Training |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Jelly Bean World: A Testbed For Never-ending Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deep Probabilistic Subsampling For Task-adaptive Compressed Sensing |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Residual Energy-based Models For Text Generation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
State-only Imitation With Transition Dynamics Mismatch |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deep Graph Matching Consensus |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Unsupervised Model Selection For Variational Disentangled Representation Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Slomo: Improving Communication-efficient Distributed Sgd With Slow Momentum |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Learning Self-correctable Policies And Value Functions From Demonstrations With Negative Sampling |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Cophy: Counterfactual Learning Of Physical Dynamics |
6 6 6 |
0.00 |
Accept (Spotlight) |
11 |
6.00 |
The Gambler’s Problem And Beyond |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Structured Object-aware Physics Prediction For Video Modeling And Planning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Combining Q-learning And Search With Amortized Value Estimates |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Robust And Interpretable Blind Image Denoising Via Bias-free Convolutional Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Vid2game: Controllable Characters Extracted From Real-world Videos |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Infinite-horizon Differentiable Model Predictive Control |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Advectivenet: An Eulerian-lagrangian Fluidic Reservoir For Point Cloud Processing |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Once For All: Train One Network And Specialize It For Efficient Deployment |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Graph Inference Learning For Semi-supervised Classification |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Theory And Evaluation Metrics For Learning Disentangled Representations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
The Implicit Bias Of Depth: How Incremental Learning Drives Generalization |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Stochastic Derivative Free Optimization Method With Momentum |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Stochastic Auc Maximization With Deep Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Metapix: Few-shot Video Retargeting |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Videoflow: A Conditional Flow-based Model For Stochastic Video Generation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Scalable Object-oriented Sequential Generative Models |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Mixup Inference: Better Exploiting Mixup To Defend Adversarial Attacks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Conservative Uncertainty Estimation By Fitting Prior Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Rapp: Novelty Detection With Reconstruction Along Projection Pathway |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Novelty Detection Via Blurring |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Detecting Extrapolation With Local Ensembles |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Learning To Solve The Credit Assignment Problem |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Pac Confidence Sets For Deep Neural Networks Via Calibrated Prediction |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Dynamical Distance Learning For Semi-supervised And Unsupervised Skill Discovery |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
The Local Elasticity Of Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Infograph: Unsupervised And Semi-supervised Graph-level Representation Learning Via Mutual Information Maximization |
6 6 6 |
0.00 |
Accept (Spotlight) |
11 |
6.00 |
Are Transformers Universal Approximators Of Sequence-to-sequence Functions? |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Stochastic Conditional Generative Networks With Basis Decomposition |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Attributes Obfuscation With Complex-valued Features |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Composition-based Multi-relational Graph Convolutional Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Structpool: Structured Graph Pooling Via Conditional Random Fields |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On Generalization Error Bounds Of Noisy Gradient Methods For Non-convex Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Target-agnostic Attack On Deep Models: Exploiting Security Vulnerabilities Of Transfer Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Meta-learning Curiosity Algorithms |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On Computation And Generalization Of Gener- Ative Adversarial Imitation Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Unrestricted Adversarial Examples Via Semantic Manipulation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Towards Neural Networks That Provably Know When They Don’t Know |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Exploration In Reinforcement Learning With Deep Covering Options |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
A Baseline For Few-shot Image Classification |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Towards Fast Adaptation Of Neural Architectures With Meta Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Cross-domain Few-shot Classification Via Learned Feature-wise Transformation |
6 6 6 |
0.00 |
Accept (Spotlight) |
11 |
6.00 |
Learning To Move With Affordance Maps |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Cm3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
To Relieve Your Headache Of Training An Mrf, Take Advil |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Analysis Of Video Feature Learning In Two-stream Cnns On The Example Of Zebrafish Swim Bout Classification |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Beyond Linearization: On Quadratic And Higher-order Approximation Of Wide Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Conditional Learning Of Fair Representations |
6 6 6 |
0.00 |
Accept (Spotlight) |
11 |
6.00 |
Curvature Graph Network |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Pruned Graph Scattering Transforms |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
The Curious Case Of Neural Text Degeneration |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Graphsaint: Graph Sampling Based Inductive Learning Method |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Learning To Coordinate Manipulation Skills Via Skill Behavior Diversification |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Expected Information Maximization: Using The I-projection For Mixture Density Estimation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Generative Ratio Matching Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Composing Task-agnostic Policies With Deep Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Selection Via Proxy: Efficient Data Selection For Deep Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Frequency-based Search-control In Dyna |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Demystifying Inter-class Disentanglement |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Continual Learning With Bayesian Neural Networks For Non-stationary Data |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Inductive And Unsupervised Representation Learning On Graph Structured Objects |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Picking Winning Tickets Before Training By Preserving Gradient Flow |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Certified Defenses For Adversarial Patches |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Multilingual Alignment Of Contextual Word Representations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Black-box Off-policy Estimation For Infinite-horizon Reinforcement Learning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Compositional Languages Emerge In A Neural Iterated Learning Model |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Rethinking The Hyperparameters For Fine-tuning |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
The Shape Of Data: Intrinsic Distance For Data Distributions |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On The Global Convergence Of Training Deep Linear Resnets |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Action Semantics Network: Considering The Effects Of Actions In Multiagent Systems |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Curriculum Loss: Robust Learning And Generalization Against Label Corruption |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Tensor Decompositions For Temporal Knowledge Base Completion |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Towards Better Understanding Of Adaptive Gradient Algorithms In Generative Adversarial Nets |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Why Not To Use Zero Imputation? Correcting Sparsity Bias In Training Neural Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Enabling Deep Spiking Neural Networks With Hybrid Conversion And Spike Timing Dependent Backpropagation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deep Audio Priors Emerge From Harmonic Convolutional Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Binaryduo: Reducing Gradient Mismatch In Binary Activation Network By Coupling Binary Activations |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Pseudo-lidar++: Accurate Depth For 3d Object Detection In Autonomous Driving |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Adjustable Real-time Style Transfer |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
You Only Train Once: Loss-conditional Training Of Deep Networks |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Progressive Memory Banks For Incremental Domain Adaptation |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Certified Robustness For Top-k Predictions Against Adversarial Perturbations Via Randomized Smoothing |
6 6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Deep Orientation Uncertainty Learning Based On A Bingham Loss |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Caql: Continuous Action Q-learning |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Identifying Through Flows For Recovering Latent Representations |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Reinforced Active Learning For Image Segmentation |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Towards A Deep Network Architecture For Structured Smoothness |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
The Variational Bandwidth Bottleneck: Stochastic Evaluation On An Information Budget |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Bounds On Over-parameterization For Guaranteed Existence Of Descent Paths In Shallow Relu Networks |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
On Bonus Based Exploration Methods In The Arcade Learning Environment |
6 6 |
0.00 |
Accept (Poster) |
11 |
6.00 |
Hierarchical Foresight: Self-supervised Learning Of Long-horizon Tasks Via Visual Subgoal Generation |
6 6 |
0.00 |
Accept (Poster) |
12 |
5.75 |
Maximum Likelihood Constraint Inference For Inverse Reinforcement Learning |
8 6 3 6 |
3.19 |
Accept (Spotlight) |
12 |
5.75 |
Autoq: Automated Kernel-wise Neural Network Quantization |
6 6 8 3 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Towards Verified Robustness Under Text Deletion Interventions |
3 6 8 6 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Mutual Information Gradient Estimation For Representation Learning |
6 3 6 8 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Computation Reallocation For Object Detection |
8 6 6 3 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Learning The Difference That Makes A Difference With Counterfactually-augmented Data |
8 6 1 8 |
8.19 |
Accept (Spotlight) |
12 |
5.75 |
Varibad: A Very Good Method For Bayes-adaptive Deep Rl Via Meta-learning |
8 6 8 1 |
8.19 |
Accept (Poster) |
12 |
5.75 |
Pcmc-net: Feature-based Pairwise Choice Markov Chains |
8 6 6 3 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Image-guided Neural Object Rendering |
6 3 8 6 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Neural Arithmetic Units |
8 3 6 6 |
3.19 |
Accept (Spotlight) |
12 |
5.75 |
Es-maml: Simple Hessian-free Meta Learning |
8 8 6 1 |
8.19 |
Accept (Poster) |
12 |
5.75 |
Probability Calibration For Knowledge Graph Embedding Models |
6 8 3 6 |
3.19 |
Accept (Poster) |
12 |
5.75 |
Span Recovery For Deep Neural Networks With Applications To Input Obfuscation |
3 6 8 6 |
3.19 |
Accept (Poster) |
12 |
5.75 |
White Noise Analysis Of Neural Networks |
6 6 8 3 |
3.19 |
Accept (Spotlight) |
13 |
5.67 |
From Inference To Generation: End-to-end Fully Self-supervised Generation Of Human Face From Speech |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Variance Reduction With Sparse Gradients |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Large Batch Optimization For Deep Learning: Training Bert In 76 Minutes |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Robust Local Features For Improving The Generalization Of Adversarial Training |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Watch, Try, Learn: Meta-learning From Demonstrations And Rewards |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Editable Neural Networks |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Prediction Poisoning: Towards Defenses Against Dnn Model Stealing Attacks |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Population-guided Parallel Policy Search For Reinforcement Learning |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Nas Evaluation Is Frustratingly Hard |
8 8 1 |
10.89 |
Accept (Poster) |
13 |
5.67 |
Learning Execution Through Neural Code Fusion |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Neural Stored-program Memory |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
A Simple Randomization Technique For Generalization In Deep Reinforcement Learning |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
On The Weaknesses Of Reinforcement Learning For Neural Machine Translation |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Self: Learning To Filter Noisy Labels With Self-ensembling |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Provable Benefit Of Orthogonal Initialization In Optimizing Deep Linear Networks |
6 3 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Emergent Tool Use From Multi-agent Autocurricula |
3 8 6 |
4.22 |
Accept (Spotlight) |
13 |
5.67 |
Sadam: A Variant Of Adam For Strongly Convex Functions |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Deep Learning Of Determinantal Point Processes Via Proper Spectral Sub-gradient |
6 3 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Meta Dropout: Learning To Perturb Latent Features For Generalization |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Functional Vs. Parametric Equivalence Of Relu Networks |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Neural Policy Gradient Methods: Global Optimality And Rates Of Convergence |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
State Alignment-based Imitation Learning |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Self-supervised Learning Of Appliance Usage |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Finding And Visualizing Weaknesses Of Deep Reinforcement Learning Agents |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Neural Oblivious Decision Ensembles For Deep Learning On Tabular Data |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Model-augmented Actor-critic: Backpropagating Through Paths |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Macer: Attack-free And Scalable Robust Training Via Maximizing Certified Radius |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Behaviour Suite For Reinforcement Learning |
8 3 6 |
4.22 |
Accept (Spotlight) |
13 |
5.67 |
Variational Hetero-encoder Randomized Gans For Joint Image-text Modeling |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Bertscore: Evaluating Text Generation With Bert |
6 3 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Learning To Explore Using Active Neural Mapping |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Learning Transport Cost From Subset Correspondence |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Generative Models For Effective Ml On Private, Decentralized Datasets |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Empirical Studies On The Properties Of Linear Regions In Deep Neural Networks |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Meta-dataset: A Dataset Of Datasets For Learning To Learn From Few Examples |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Compositional Continual Language Learning |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Data-independent Neural Pruning Via Coresets |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Learning Heuristics For Quantified Boolean Formulas Through Reinforcement Learning |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Augmenting Genetic Algorithms With Deep Neural Networks For Exploring The Chemical Space |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
A Signal Propagation Perspective For Pruning Neural Networks At Initialization |
6 8 3 |
4.22 |
Accept (Spotlight) |
13 |
5.67 |
Neural Tangents: Fast And Easy Infinite Neural Networks In Python |
3 8 6 |
4.22 |
Accept (Spotlight) |
13 |
5.67 |
Structbert: Incorporating Language Structures Into Pre-training For Deep Language Understanding |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Nas-bench-1shot1: Benchmarking And Dissecting One-shot Neural Architecture Search |
8 8 1 |
10.89 |
Accept (Poster) |
13 |
5.67 |
Adversarially Robust Representations With Smooth Encoders |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Iterative Energy-based Projection On A Normal Data Manifold For Anomaly Localization |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Bridging Mode Connectivity In Loss Landscapes And Adversarial Robustness |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Identity Crisis: Memorization And Generalization Under Extreme Overparameterization |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
B-spline Cnns On Lie Groups |
6 3 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Adversarially Robust Transfer Learning |
1 8 8 |
10.89 |
Accept (Poster) |
13 |
5.67 |
Improved Memory In Recurrent Neural Networks With Sequential Non-normal Dynamics |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Towards Stable And Efficient Training Of Verifiably Robust Neural Networks |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Transferring Optimality Across Data Distributions Via Homotopy Methods |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
The Asymptotic Spectrum Of The Hessian Of Dnn Throughout Training |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Learn To Explain Efficiently Via Neural Logic Inductive Learning |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Robust Training With Ensemble Consensus |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Domain Adaptive Multiflow Networks |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Distributionally Robust Neural Networks |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Learning To Group: A Bottom-up Framework For 3d Part Discovery In Unseen Categories |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
The Early Phase Of Neural Network Training |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Extreme Classification Via Adversarial Softmax Approximation |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Convergence Behaviour Of Some Gradient-based Methods On Bilinear Zero-sum Games |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Gradients As Features For Deep Representation Learning |
8 3 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Capsules With Inverted Dot-product Attention Routing |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Implicit Bias Of Gradient Descent Based Adversarial Training On Separable Data |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Understanding Architectures Learnt By Cell-based Neural Architecture Search |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Maxmin Q-learning: Controlling The Estimation Bias Of Q-learning |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Kernel Of Cyclegan As A Principal Homogeneous Space |
8 6 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Neural Execution Of Graph Algorithms |
1 8 8 |
10.89 |
Accept (Poster) |
13 |
5.67 |
On Need For Topology-aware Generative Models For Manifold-based Defenses |
3 8 6 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Universal Approximation With Certified Networks |
6 8 3 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Discovering Motor Programs By Recomposing Demonstrations |
3 6 8 |
4.22 |
Accept (Poster) |
13 |
5.67 |
Hypermodels For Exploration |
8 3 6 |
4.22 |
Accept (Poster) |
14 |
5.50 |
Sub-policy Adaptation For Hierarchical Reinforcement Learning |
3 8 |
6.25 |
Accept (Poster) |
14 |
5.50 |
Pairnorm: Tackling Oversmoothing In Gnns |
3 8 |
6.25 |
Accept (Poster) |
14 |
5.50 |
Svqn: Sequential Variational Soft Q-learning Networks |
3 8 |
6.25 |
Accept (Poster) |
14 |
5.50 |
Cln2inv: Learning Loop Invariants With Continuous Logic Networks |
3 8 |
6.25 |
Accept (Poster) |
15 |
5.25 |
Spatially Parallel Attention And Component Extraction For Scene Decomposition |
6 6 3 6 |
1.69 |
Accept (Poster) |
15 |
5.25 |
Impact: Importance Weighted Asynchronous Architectures With Clipped Target Networks |
6 3 6 6 |
1.69 |
Accept (Poster) |
15 |
5.25 |
Shifted And Squeezed 8-bit Floating Point Format For Low-precision Training Of Deep Neural Networks |
6 8 1 6 |
6.69 |
Accept (Poster) |
15 |
5.25 |
Visual Representation Learning With 3d View-constrastive Inverse Graphics Networks |
3 6 6 6 |
1.69 |
Accept (Poster) |
16 |
5.00 |
V4d: 4d Convonlutional Neural Networks For Video-level Representation Learning |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Ranking Policy Gradient |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Regularizing Activations In Neural Networks Via Distribution Matching With The Wassertein Metric |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Cross-lingual Ability Of Multilingual Bert: An Empirical Study |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Abstract Diagrammatic Reasoning With Multiplex Graph Networks |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Augmenting Non-collaborative Dialog Systems With Explicit Semantic And Strategic Dialog History |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Mma Training: Direct Input Space Margin Maximization Through Adversarial Training |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Generalized Convolutional Forest Networks For Domain Generalization And Visual Recognition |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Weakly Supervised Clustering By Exploiting Unique Class Count |
8 1 6 |
8.67 |
Accept (Poster) |
16 |
5.00 |
Additive Powers-of-two Quantization: A Non-uniform Discretization For Neural Networks |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Jacobian Adversarially Regularized Networks For Robustness |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Lamol: Language Modeling For Lifelong Language Learning |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Training Recurrent Neural Networks Online By Learning Explicit State Variables |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Relational State-space Model For Stochastic Multi-object Systems |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Stochastic Weight Averaging In Parallel: Large-batch Training That Generalizes Well |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Bayesian Meta Sampling For Fast Uncertainty Adaptation |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Phase Transitions For The Information Bottleneck In Representation Learning |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Neural Text Generation With Unlikelihood Training |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Model-based Reinforcement Learning For Biological Sequence Design |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Depth-adaptive Transformer |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Critical Initialisation In Continuous Approximations Of Binary Neural Networks |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Prox-sgd: Training Structured Neural Networks Under Regularization And Constraints |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Bayesopt Adversarial Attack |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Chameleon: Adaptive Code Optimization For Expedited Deep Neural Network Compilation |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Learning Nearly Decomposable Value Functions Via Communication Minimization |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Difference-seeking Generative Adversarial Network–unseen Sample Generation |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Learning Deep Graph Matching With Channel-independent Embedding And Hungarian Attention |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Robust Anomaly Detection And Backdoor Attack Detection Via Differential Privacy |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Robustness Verification For Transformers |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Implementing Inductive Bias For Different Navigation Tasks Through Diverse Rnn Attrractors |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Enhancing Transformation-based Defenses Against Adversarial Attacks With A Distribution Classifier |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Functional Regularisation For Continual Learning With Gaussian Processes |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Toward Evaluating Robustness Of Deep Reinforcement Learning With Continuous Control |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Learning Efficient Parameter Server Synchronization Policies For Distributed Sgd |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Understanding Why Neural Networks Generalize Well Through Gsnr Of Parameters |
6 3 6 |
2.00 |
Accept (Spotlight) |
16 |
5.00 |
Smoothness And Stability In Gans |
8 6 1 |
8.67 |
Accept (Poster) |
16 |
5.00 |
Plug And Play Language Model: A Simple Baseline For Controlled Language Generation |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
A Constructive Prediction Of The Generalization Error Across Scales |
1 6 8 |
8.67 |
Accept (Poster) |
16 |
5.00 |
Contrastive Representation Distillation |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Differentiable Learning Of Numerical Rules In Knowledge Graphs |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Infinite-horizon Off-policy Policy Evaluation With Multiple Behavior Policies |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Rgbd-gan: Unsupervised 3d Representation Learning From Natural Image Datasets Via Rgbd Image Synthesis |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Generalization Through Memorization: Nearest Neighbor Language Models |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Decentralized Deep Learning With Arbitrary Communication Compression |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Escaping Saddle Points Faster With Stochastic Momentum |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Linear Symmetric Quantization Of Neural Networks For Low-precision Integer Hardware |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Nesterov Accelerated Gradient And Scale Invariance For Adversarial Attacks |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Scalable And Order-robust Continual Learning With Additive Parameter Decomposition |
8 1 6 |
8.67 |
Accept (Poster) |
16 |
5.00 |
Four Things Everyone Should Know To Improve Batch Normalization |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Define: Deep Factorized Input Word Embeddings For Neural Sequence Modeling |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Neural Epitome Search For Architecture-agnostic Network Compression |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Efficient Riemannian Optimization On The Stiefel Manifold Via The Cayley Transform |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Federated Adversarial Domain Adaptation |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
How To 0wn The Nas In Your Spare Time |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Deep 3d Pan Via Local Adaptive “t-shaped” Convolutions With Global And Local Adaptive Dilations |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Efficient And Information-preserving Future Frame Prediction And Beyond |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Episodic Reinforcement Learning With Associative Memory |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Higher-order Function Networks For Learning Composable 3d Object Representations |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Atomnas: Fine-grained End-to-end Neural Architecture Search |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Learning Space Partitions For Nearest Neighbor Search |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Few-shot Learning On Graphs Via Super-classes Based On Graph Spectral Measures |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Nonlinearities In Activations Substantially Shape The Loss Surfaces Of Neural Networks |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Global Relational Models Of Source Code |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Improving Neural Language Generation With Spectrum Control |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Batchensemble: An Alternative Approach To Efficient Ensemble And Lifelong Learning |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Differentiable Programming For Physical Simulation |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Duration-of-stay Storage Assignment Under Uncertainty |
6 3 6 |
2.00 |
Accept (Spotlight) |
16 |
5.00 |
Locally Constant Networks |
3 6 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Blockswap: Fisher-guided Block Substitution For Network Compression On A Budget |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Vl-bert: Pre-training Of Generic Visual-linguistic Representations |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Deep Symbolic Superoptimization Without Human Knowledge |
6 3 6 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Automatically Discovering And Learning New Visual Categories With Ranking Statistics |
6 6 3 |
2.00 |
Accept (Poster) |
16 |
5.00 |
Semantically-guided Representation Learning For Self-supervised Monocular Depth |
3 6 6 |
2.00 |
Accept (Poster) |
17 |
4.67 |
Pure And Spurious Critical Points: A Geometric Study Of Linear Networks |
3 3 8 |
5.56 |
Accept (Poster) |
17 |
4.67 |
Ae-ot: A New Generative Model Based On Extended Semi-discrete Optimal Transport |
3 8 3 |
5.56 |
Accept (Poster) |
17 |
4.67 |
I Am Going Mad: Maximum Discrepancy Competition For Comparing Classifiers Adaptively |
3 3 8 |
5.56 |
Accept (Poster) |
17 |
4.67 |
Continual Learning With Adaptive Weights (claw) |
3 8 3 |
5.56 |
Accept (Poster) |
17 |
4.67 |
Logic And The 2-simplicial Transformer |
8 3 3 |
5.56 |
Accept (Poster) |
18 |
4.50 |
Sign-opt: A Query-efficient Hard-label Adversarial Attack |
3 6 |
2.25 |
Accept (Poster) |
18 |
4.50 |
Short And Sparse Deconvolution — A Geometric Approach |
3 6 |
2.25 |
Accept (Poster) |
19 |
4.33 |
Learning To Represent Programs With Property Signatures |
1 6 6 |
5.56 |
Accept (Poster) |
19 |
4.33 |
Disentangling Factors Of Variations Using Few Labels |
6 6 1 |
5.56 |
Accept (Poster) |
19 |
4.33 |
Empir: Ensembles Of Mixed Precision Deep Networks For Increased Robustness Against Adversarial Attacks |
1 6 6 |
5.56 |
Accept (Poster) |
19 |
4.33 |
Non-autoregressive Dialog State Tracking |
6 1 6 |
5.56 |
Accept (Poster) |
19 |
4.33 |
Going Beyond Token-level Pre-training For Embedding-based Large-scale Retrieval |
1 6 6 |
5.56 |
Accept (Poster) |
19 |
4.33 |
A Critical Analysis Of Self-supervision, Or What We Can Learn From A Single Image |
6 1 6 |
5.56 |
Accept (Poster) |
19 |
4.33 |
Overlearning Reveals Sensitive Attributes |
6 1 6 |
5.56 |
Accept (Poster) |
20 |
4.00 |
Exploratory Not Explanatory: Counterfactual Analysis Of Saliency Maps For Deep Rl |
1 3 8 |
8.67 |
Accept (Poster) |
20 |
4.00 |
Gap-aware Mitigation Of Gradient Staleness |
6 3 3 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Input Complexity And Out-of-distribution Detection With Likelihood-based Generative Models |
6 3 3 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Size-free Generalization Bounds For Convolutional Neural Networks |
6 3 3 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Fair Resource Allocation In Federated Learning |
3 3 6 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Dropedge: Towards Deep Graph Convolutional Networks On Node Classification |
6 3 3 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Provable Filter Pruning For Efficient Neural Networks |
3 6 3 |
2.00 |
Accept (Poster) |
20 |
4.00 |
Playing The Lottery With Rewards And Multiple Languages: Lottery Tickets In Rl And Nlp |
3 3 6 |
2.00 |
Accept (Poster) |
21 |
3.33 |
Few-shot Text Classification With Distributional Signatures |
6 1 3 |
4.22 |
Accept (Poster) |
22 |
2.33 |
Efficient Probabilistic Logic Reasoning With Graph Neural Networks |
1 3 3 |
0.89 |
Accept (Poster) |