NeurIPS 2020

Search Schedule »

Search:

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

Dec. 6, 2020 Expo schedule » New in ML »

Timezone: US/Pacific »

Indicates the beginning of a session

Time	Orals & Spotlights: Reinforcement Learning	Orals & Spotlights: COVID/Health/Bio Applications	Orals & Spotlights: Language/Audio Applications	Orals & Spotlights: Representation/Relational	Poster Session 0	Virtual
Mon Dec 07, 2020
12:00 AM (Tutorials)						Tutorial Track 2A (Track2) Deeper Conversational AI
08:00 AM (Tutorials)						(Track2) Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning (Track1) Advances in Approximate Inference
06:00 PM (Orals)	Orals & Spotlights Track 04: Reinforcement Learning An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search	Orals & Spotlights Track 02: COVID/Health/Bio Applications When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes	Orals & Spotlights Track 03: Language/Audio Applications Language Models are Few-Shot Learners	Orals & Spotlights Track 01: Representation/Relational Learning Physical Graph Representations from Visual Scenes
06:15 PM (Orals)	Novelty Search in Representational Space for Sample Efficient Exploration	Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement	Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search	Multi-label Contrastive Predictive Coding
06:30 PM (Orals)	Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design	Neural encoding with visual attention	The Cone of Silence: Speech Separation by Localization	Equivariant Networks for Hierarchical Structures
07:00 PM (Spotlights)	First Order Constrained Optimization in Policy Space	Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations	Unsupervised Sound Separation Using Mixture Invariant Training	On the Equivalence between Online and Private Learnability beyond Binary Classification
07:10 PM (Spotlights)	CoinDICE: Off-Policy Confidence Interval Estimation	Using noise to probe recurrent neural network structure and prune synapses	Investigating Gender Bias in Language Models Using Causal Mediation Analysis	Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
07:20 PM (Spotlights)	DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction	Interpretable Sequence Learning for Covid-19 Forecasting	A Simple Language Model for Task-Oriented Dialogue	Joint Contrastive Learning with Infinite Possibilities
07:30 PM (Spotlights)	Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret	Kalman Filtering Attention for User Behavior Modeling in CTR Prediction	ConvBERT: Improving BERT with Span-based Dynamic Convolution	Neural Methods for Point-wise Dependency Estimation
07:50 PM (Spotlights)	Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning	Demixed shared component analysis of neural population data from multiple brain areas	Cross-lingual Retrieval for Iterative Self-Supervised Training	Design Space for Graph Neural Networks
08:00 PM (Spotlights)	Bayesian Multi-type Mean Field Multi-agent Imitation Learning	Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects	DynaBERT: Dynamic BERT with Adaptive Width and Depth	Debiased Contrastive Learning
08:10 PM (Spotlights)	Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity	The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models	Incorporating Pragmatic Reasoning Communication into Emergent Language	The Autoencoding Variational Autoencoder
08:20 PM (Spotlights)	Safe Reinforcement Learning via Curriculum Induction		De-Anonymizing Text by Fingerprinting Language Generation	Unsupervised Representation Learning by Invariance Propagation
09:00 PM (Posters)					Poster Session 1

Time	Orals & Spotlights: Vision Applications	Orals & Spotlights: Reinforcement Learning	Orals & Spotlights: Deep Learning	Orals & Spotlights: Social/Privacy	Orals & Spotlights: Clustering/Ranking	Orals & Spotlights: Dynamical Sys/Density/Sparsity	Orals & Spotlights: Learning Theory	Orals & Spotlights: Deep Learning/Theory	Poster Session 1	Poster Session 2
Tue Dec 08, 2020
06:00 AM (Orals)	Orals & Spotlights Track 07: Vision Applications Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring	Orals & Spotlights Track 09: Reinforcement Learning Improved Sample Complexity for Incremental Autonomous Exploration in MDPs	Orals & Spotlights Track 08: Deep Learning Multiscale Deep Equilibrium Models	Orals & Spotlights Track 10: Social/Privacy Adversarially Robust Streaming Algorithms via Differential Privacy	Orals & Spotlights Track 05: Clustering/Ranking Exact Recovery of Mangled Clusters with Same-Cluster Queries	Orals & Spotlights Track 06: Dynamical Sys/Density/Sparsity Deep Energy-based Modeling of Discrete-Time Physics	Orals & Spotlights Track 11: Learning Theory No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
06:15 AM (Orals)	Causal Intervention for Weakly-Supervised Semantic Segmentation	Escaping the Gravitational Pull of Softmax	On the Modularity of Hypernetworks	Differentially Private Clustering: Tight Approximation Ratios	Deep Transformation-Invariant Clustering	SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory	Efficient active learning of sparse halfspaces with arbitrary bounded noise
06:30 AM (Orals)	Convolutional Generation of Textured 3D Meshes	FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs	Training Generative Adversarial Networks with Limited Data	Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms	Partially View-aligned Clustering	Dissecting Neural ODEs	Learning Parities with Neural Networks
07:00 AM (Spotlights)	DISK: Learning local features with policy gradient	Interferobot: aligning an optical interferometer by a reinforcement learning agent	MeshSDF: Differentiable Iso-Surface Extraction	Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates	Simple and Scalable Sparse k-means Clustering via Feature Ranking	Robust Density Estimation under Besov IPM Losses	The Adaptive Complexity of Maximizing a Gross Substitutes Valuation
07:10 AM (Spotlights)	Wasserstein Distances for Stereo Disparity Estimation	On Efficiency in Hierarchical Reinforcement Learning	GAIT-prop: A biologically plausible learning rule derived from backpropagation of error	Private Identity Testing for High-Dimensional Distributions	Simultaneous Preference and Metric Learning from Paired Comparisons	Almost Surely Stable Deep Dynamics	Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics
07:20 AM (Spotlights)	Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance	Finite-Time Analysis for Double Q-learning	Monotone operator equilibrium networks	Permute-and-Flip: A new mechanism for differentially private selection	Learning Optimal Representations with the Decodable Information Bottleneck	Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks	A Bandit Learning Algorithm and Applications to Auction Design
07:30 AM (Spotlights)	Learning Semantic-aware Normalization for Generative Adversarial Networks	Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes	What Do Neural Networks Learn When Trained With Random Labels?	Smoothed Analysis of Online and Differentially Private Learning	Manifold structure in graph embeddings	A Theoretical Framework for Target Propagation	An Optimal Elimination Algorithm for Learning a Best Arm
07:50 AM (Spotlights)	Neural Sparse Voxel Fields	Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning	H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks	Optimal Private Median Estimation under Minimal Distributional Assumptions	Self-Supervised Learning by Cross-Modal Audio-Video Clustering	Training Generative Adversarial Networks by Solving Ordinary Differential Equations	Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
08:00 AM (Spotlights)	3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data	Model-based Policy Optimization with Unsupervised Model Adaptation	ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks	Assisted Learning: A Framework for Multi-Organization Learning	Classification with Valid and Adaptive Coverage	Information theoretic limits of learning a sparse rule	PAC-Bayesian Bound for the Conditional Value at Risk
08:10 AM (Spotlights)	Learning to Detect Objects with a 1 Megapixel Event Camera	Variational Policy Gradient Method for Reinforcement Learning with General Utilities	The phase diagram of approximation rates for deep neural networks	Higher-Order Certification For Randomized Smoothing	On ranking via sorting by estimated expected utility	Constant-Expansion Suffices for Compressed Sensing with Generative Priors	Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability
08:20 AM (Spotlights)	A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection	Sample-Efficient Reinforcement Learning of Undercomplete POMDPs	Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient			Logarithmic Pruning is All You Need	Hedging in games: Faster convergence of external and swap regrets
08:30 AM (Spotlights)							Online Bayesian Persuasion
09:00 AM (Posters)									Poster Session 2
06:00 PM (Orals)	Orals & Spotlights Track 12: Vision Applications Space-Time Correspondence as a Contrastive Random Walk	Orals & Spotlights Track 14: Reinforcement Learning Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement						Orals & Spotlights Track 13: Deep Learning/Theory Implicit Neural Representations with Periodic Activation Functions
06:15 PM (Orals)	Rethinking Pre-training and Self-training	Learning Individually Inferred Communication for Multi-Agent Cooperation						Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
06:30 PM (Orals)	Do Adversarially Robust ImageNet Models Transfer Better?	Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory						Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
07:00 PM (Spotlights)	Self-Supervised Visual Representation Learning from Hierarchical Grouping	Reinforcement Learning with Augmented Data						MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
07:10 PM (Spotlights)	Learning Affordance Landscapes for Interaction Exploration in 3D Environments	Sub-sampling for Efficient Non-Parametric Bandit Exploration						Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
07:20 PM (Spotlights)	Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D	Language-Conditioned Imitation Learning for Robot Manipulation Tasks						Compositional Visual Generation with Energy Based Models
07:30 PM (Spotlights)	Large-Scale Adversarial Training for Vision-and-Language Representation Learning	High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization						Certified Monotonic Neural Networks
07:50 PM (Spotlights)	Measuring Robustness to Natural Distribution Shifts in Image Classification	Policy Improvement via Imitation of Multiple Oracles						Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
08:00 PM (Spotlights)	Curriculum By Smoothing	Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning						On Correctness of Automatic Differentiation for Non-Differentiable Functions
08:10 PM (Spotlights)	Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies	Avoiding Side Effects in Complex Environments						The Complete Lasso Tradeoff Diagram
08:20 PM (Spotlights)		Preference-based Reinforcement Learning with Finite-Time Guarantees						Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
09:00 PM (Posters)										Poster Session 3

Time	Orals & Spotlights: Vision Applications	Orals & Spotlights: Deep Learning	Orals & Spotlights: COVID/Applications/Composition	Orals & Spotlights: Continual/Meta/Misc Learning	Orals & Spotlights: Kernel Methods/Optimization	Orals & Spotlights: Optimization	Orals & Spotlights: Probabilistic/Causality	Orals & Spotlights: Social/Adversarial Learning	Orals & Spotlights: Learning Theory	Orals & Spotlights: Graph/Meta Learning/Software	Poster Session 3	Poster Session 4
Wed Dec 09, 2020
06:00 AM (Orals)		Orals & Spotlights Track 18: Deep Learning Ultra-Low Precision 4-bit Training of Deep Neural Networks	Orals & Spotlights Track 15: COVID/Applications/Composition High-Fidelity Generative Image Compression	Orals & Spotlights Track 16: Continual/Meta/Misc Learning Continual Deep Learning by Functional Regularisation of Memorable Past	Orals & Spotlights Track 17: Kernel Methods/Optimization Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces	Orals & Spotlights Track 21: Optimization Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent	Orals & Spotlights Track 19: Probabilistic/Causality Network-to-Network Translation with Conditional Invertible Neural Networks	Orals & Spotlights Track 20: Social/Adversarial Learning DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
06:15 AM (Orals)		Reservoir Computing meets Recurrent Kernels and Structured Transforms	Learning Composable Energy Surrogates for PDE Order Reduction	Look-ahead Meta Learning for Continual Learning	Kernel Methods Through the Roof: Handling Billions of Points Efficiently	Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form	Causal Imitation Learning With Unobserved Confounders	Metric-Free Individual Fairness in Online Learning
06:30 AM (Orals)		The interplay between randomness and structure during learning in RNNs	Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems	NeuMiss networks: differentiable programming for supervised learning with missing values.	A Group-Theoretic Framework for Data Augmentation	Acceleration with a Ball Optimization Oracle	Gradient Estimation with Stochastic Softmax Tricks	Fair regression via plug-in estimator and recalibration with statistical guarantees
06:45 AM (Orals)						Convex optimization based on global lower second-order models
07:00 AM (Spotlights)		What if Neural Networks had SVDs?	Compositional Generalization by Learning Analytical Expressions	Meta-trained agents implement Bayes-optimal agents	A mathematical model for automatic differentiation in machine learning	Adam with Bandit Sampling for Deep Learning	Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs	Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay
07:10 AM (Spotlights)		Practical Quasi-Newton Methods for Training Deep Neural Networks	Modern Hopfield Networks and Attention for Immune Repertoire Classification	Linear Dynamical Systems as a Core Computational Primitive	A kernel test for quasi-independence	Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling	A Randomized Algorithm to Reduce the Support of Discrete Measures	Differentially-Private Federated Linear Bandits
07:20 AM (Spotlights)		Triple descent and the two kinds of overfitting: where & why do they appear?	ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA	Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels	Fourier Sparse Leverage Scores and Approximate Kernel Learning	IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method	A/B Testing in Dense Large-Scale Networks: Design and Inference	Adversarial Training is a Form of Data-dependent Operator Norm Regularization
07:30 AM (Spotlights)		On the linearity of large non-linear models: when and why the tangent kernel is constant	A causal view of compositional zero-shot recognition	Uncertainty-aware Self-training for Few-shot Text Classification	BOSS: Bayesian Optimization over String Spaces	Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity	DisARM: An Antithetic Gradient Estimator for Binary Latent Variables	Prediction with Corrupted Expert Advice
07:50 AM (Spotlights)		Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy	RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist	HiPPO: Recurrent Memory with Optimal Polynomial Projections	Fast geometric learning with symbolic matrices	Minibatch Stochastic Approximate Proximal Point Methods	Off-Policy Evaluation and Learning for External Validity under a Covariate Shift	Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
08:00 AM (Spotlights)		Proximal Mapping for Deep Regularization	Barking up the right tree: an approach to search over molecule synthesis DAGs	Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity	Training Stronger Baselines for Learning to Optimize	Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems	Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding	Towards Safe Policy Improvement for Non-Stationary MDPs
08:10 AM (Spotlights)		BoxE: A Box Embedding Model for Knowledge Base Completion	Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views	Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge	Learning Linear Programs from Optimal Decisions	Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms	Differentiable Causal Discovery from Interventional Data	Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
08:20 AM (Spotlights)			Experimental design for MRI by greedy policy search	Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning	Automatically Learning Compact Quality-aware Surrogates for Optimization Problems	Linearly Converging Error Compensated SGD	Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks	Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
08:30 AM (Spotlights)			How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?	Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients		Learning Augmented Energy Minimization via Speed Scaling	Efficient semidefinite-programming-based inference for binary and multi-class MRFs	Understanding Gradient Clipping in Private SGD: A Geometric Perspective
09:00 AM (Posters)											Poster Session 4
06:00 PM (Orals)	Orals & Spotlights Track 22: Vision Applications Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence								Orals & Spotlights Track 24: Learning Theory Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method	Orals & Spotlights Track 23: Graph/Meta Learning/Software FrugalML: How to use ML Prediction APIs more accurately and cheaply
06:15 PM (Orals)	LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration								Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs	AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
06:30 PM (Orals)	The Origins and Prevalence of Texture Bias in Convolutional Neural Networks								Worst-Case Analysis for Randomly Collected Data	PyGlove: Symbolic Programming for Automated Machine Learning
07:00 PM (Spotlights)	Distribution Matching for Crowd Counting								On Adaptive Distance Estimation	Improved Schemes for Episodic Memory-based Lifelong Learning
07:10 PM (Spotlights)	Texture Interpolation for Probing Visual Perception								Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits	Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
07:20 PM (Spotlights)	Consistent Structural Relation Learning for Zero-Shot Segmentation								Delay and Cooperation in Nonstochastic Linear Bandits	Uncertainty Aware Semi-Supervised Learning on Graph Data
07:30 PM (Spotlights)	CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations								Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms	Rethinking Importance Weighting for Deep Learning under Distribution Shift
07:50 PM (Spotlights)	ShapeFlow: Learnable Deformation Flows Among 3D Shapes								Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition	Modular Meta-Learning with Shrinkage
08:00 PM (Spotlights)	Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows								A Tight Lower Bound and Efficient Reduction for Swap Regret	JAX MD: A Framework for Differentiable Physics
08:10 PM (Spotlights)	Counterfactual Vision-and-Language Navigation: Unravelling the Unseen								Estimation of Skill Distribution from a Tournament	RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
08:20 PM (Spotlights)	RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder								Optimal Prediction of the Number of Unseen Species with Multiplicity
08:30 PM (Spotlights)									Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks
09:00 PM (Posters)												Poster Session 5

Time	Orals & Spotlights: Reinforcement Learning	Orals & Spotlights: Deep Learning	Orals & Spotlights: Unsupervised/Probabilistic	Orals & Spotlights: Probabilistic Models/Statistics	Orals & Spotlights: Graph/Relational/Theory	Orals & Spotlights: Neuroscience	Orals & Spotlights: Optimization	Orals & Spotlights: Optimization/Theory	Orals & Spotlights: Health/AutoML/(Soft\|Hard)ware	Orals & Spotlights: Neuroscience/Probabilistic	Poster Session 5	Poster Session 6
Thu Dec 10, 2020
06:00 AM (Orals)	Orals & Spotlights Track 31: Reinforcement Learning Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs	Orals & Spotlights Track 28: Deep Learning A shooting formulation of deep learning	Orals & Spotlights Track 27: Unsupervised/Probabilistic Contrastive learning of global and local features for medical image segmentation with limited annotations	Orals & Spotlights Track 25: Probabilistic Models/Statistics Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification	Orals & Spotlights Track 26: Graph/Relational/Theory Graph Cross Networks with Vertex Infomax Pooling	Orals & Spotlights Track 29: Neuroscience Learning abstract structure for drawing by efficient motor program induction		Orals & Spotlights Track 30: Optimization/Theory Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
06:15 AM (Orals)	Self-Paced Deep Reinforcement Learning	On the training dynamics of deep networks with $L_2$ regularization	Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning	Fast and Flexible Temporal Point Processes with Triangular Maps	Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs	Non-reversible Gaussian processes for identifying latent dynamical structure in neural data		Towards a Better Global Loss Landscape of GANs
06:30 AM (Orals)	Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning	Compositional Explanations of Neurons	SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows	Greedy inference with structure-exploiting lazy maps	Graph Random Neural Networks for Semi-Supervised Learning on Graphs	Gibbs Sampling with People		Online Sinkhorn: Optimal Transport distances from sample streams
07:00 AM (Spotlights)	Bandit Linear Control	Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints	Self-Supervised Relational Reasoning for Representation Learning	Sampling from a k-DPP without looking at all items	Learning Graph Structure With A Finite-State Automaton Layer	Stable and expressive recurrent vision models		Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
07:10 AM (Spotlights)	Neural Dynamic Policies for End-to-End Sensorimotor Learning	On Power Laws in Deep Ensembles	Object-Centric Learning with Slot Attention	Non-parametric Models for Non-negative Functions	Pointer Graph Networks	Identifying Learning Rules From Neural Network Observables		Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions
07:20 AM (Spotlights)	Effective Diversity in Population Based Reinforcement Learning	Learning the Geometry of Wave-Based Imaging	Telescoping Density-Ratio Estimation	Distribution-free binary classification: prediction sets, confidence intervals and calibration		A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons		Conformal Symplectic and Relativistic Optimization
07:30 AM (Spotlights)	Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization	The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks	Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations	Factor Graph Grammars	Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks	Modeling Shared responses in Neuroimaging Studies through MultiView ICA		Random Reshuffling is Not Always Better
07:50 AM (Spotlights)	Reward Propagation Using Graph Convolutional Networks	Sparse and Continuous Attention Mechanisms	Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks	Asymptotically Optimal Exact Minibatch Metropolis-Hastings	Convergence and Stability of Graph Convolutional Networks on Large Random Graphs	Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning		The Statistical Complexity of Early-Stopped Mirror Descent
08:00 AM (Spotlights)	On the Convergence of Smooth Regularized Approximate Value Iteration Schemes	Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks	Stochastic Normalizing Flows	Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class	Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains	Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence		Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
08:10 AM (Spotlights)	Latent World Models For Intrinsically Motivated Exploration	Directional convergence and alignment in deep learning	Generative Neurosymbolic Machines	Confidence sequences for sampling without replacement	Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations	System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina		Towards Problem-dependent Optimal Learning Rates
08:20 AM (Spotlights)	Learning to Play No-Press Diplomacy with Best Response Policy Iteration	Neural Controlled Differential Equations for Irregular Time Series	DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks	Statistical and Topological Properties of Sliced Probability Divergences	Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples	A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network		On Uniform Convergence and Low-Norm Interpolation Learning
08:30 AM (Spotlights)				Testing Determinantal Point Processes
09:00 AM (Posters)											Poster Session 6
06:00 PM (Orals)		Orals & Spotlights Track 34: Deep Learning Is normalization indispensable for training deep neural network?					Orals & Spotlights Track 32: Optimization Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization		Orals & Spotlights Track 33: Health/AutoML/(Soft\|Hard)ware Theory-Inspired Path-Regularized Differential Network Architecture Search	Orals & Spotlights Track 35: Neuroscience/Probabilistic Point process models for sequence detection in high-dimensional neural spike trains
06:15 PM (Orals)		Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks					The Primal-Dual method for Learning Augmented Algorithms		Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows	Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
06:30 PM (Orals)		Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks					Fully Dynamic Algorithm for Constrained Submodular Optimization		Transferable Graph Optimizers for ML Compilers	A mathematical theory of cooperative communication
07:00 PM (Spotlights)		Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics					Submodular Maximization Through Barrier Functions		A Study on Encodings for Neural Architecture Search	Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
07:10 PM (Spotlights)		Kernel Based Progressive Distillation for Adder Neural Networks					Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method		Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding	Sinkhorn Natural Gradient for Generative Models
07:20 PM (Spotlights)		What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation					A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints		Evolving Normalization-Activation Layers	NVAE: A Deep Hierarchical Variational Autoencoder
07:30 PM (Spotlights)		Collegial Ensembles					How many samples is a good initial point worth in Low-rank Matrix Recovery?		Open Graph Benchmark: Datasets for Machine Learning on Graphs	Reciprocal Adversarial Learning via Characteristic Functions
07:50 PM (Spotlights)		Finite Versus Infinite Neural Networks: an Empirical Study					Projection Robust Wasserstein Distance and Riemannian Optimization		Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning	Incorporating Interpretable Output Constraints in Bayesian Neural Networks
08:00 PM (Spotlights)		Estimating Training Data Influence by Tracing Gradient Descent					A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval		MCUNet: Tiny Deep Learning on IoT Devices	Baxter Permutation Process
08:10 PM (Spotlights)		AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients					SGD with shuffling: optimal rates without component convexity and large epoch requirements		Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming	Flexible mean field variational inference using mixtures of non-overlapping exponential families
08:20 PM (Spotlights)		Part-dependent Label Noise: Towards Instance-dependent Label Noise					No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix
09:00 PM (Posters)												Poster Session 7

Mon Dec 07, 2020

Tue Dec 08, 2020

Wed Dec 09, 2020

Thu Dec 10, 2020