AISTATS 2021 Papers

Skip to yearly menu bar Skip to main content

Browse

mini compact topic detail

Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce Model

Interpretable Random Forests via Rule Extraction

Regret Minimization for Causal Inference on Large Treatment Space

Bayesian Model Averaging for Causality Estimation and its Approximation based on Gaussian Scale Mixture Distributions

Adaptive Sampling for Fast Constrained Maximization of Submodular Functions

Mean-Variance Analysis in Bayesian Optimization under Uncertainty

Hadamard Wirtinger Flow for Sparse Phase Retrieval

Stochastic Linear Bandits Robust to Adversarial Attacks

ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning

Optimizing Percentile Criterion using Robust MDPs

On Riemannian Stochastic Approximation Schemes with Fixed Step-Size

Optimal Quantisation of Probability Measures Using Maximum Mean Discrepancy

Aligning Time Series on Incomparable Spaces

The Unexpected Deterministic and Universal Behavior of Large Softmax Classifiers

Measure Transport with Kernel Stein Discrepancy

Unifying Clustered and Non-stationary Bandits

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

Transforming Gaussian Processes With Normalizing Flows

Linearly Constrained Gaussian Processes with Boundary Conditions

Noise Contrastive Meta-Learning for ConditionalDensity Estimation using Kernel Mean Embeddings

Top-m identification for linear bandits

Online k-means Clustering

Consistent k-Median: Simpler, Better and Robust

Algorithms for Fairness in Sequential Decision Making

On Learning Continuous Pairwise Markov Random Fields

Abstract Value Iteration for Hierarchical Reinforcement Learning

Differentially Private Analysis on Graph Streams

Learning with Hyperspherical Uniformity

Finding First-Order Nash Equilibria of Zero-Sum Games with the Regularized Nikaido-Isoda Function

Latent Derivative Bayesian Last Layer Networks

Provably Safe PAC-MDP Exploration Using Analogies

Maximal Couplings of the Metropolis-Hastings Algorithm

Goodness-of-Fit Test for Mismatched Self-Exciting Processes

Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship

A Study of Condition Numbers for First-Order Optimization

Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions

Differentially Private Online Submodular Maximization

Anderson acceleration of coordinate descent

Inference in Stochastic Epidemic Models via Multinomial Approximations

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence

SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation

Stable ResNet

Latent variable modeling with random features

Reaping the Benefits of Bundling under High Production Costs

Momentum Improves Optimization on Riemannian Manifolds

Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear Time

On Data Efficiency of Meta-learning

Hyperparameter Transfer Learning with Adaptive Complexity

Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency

Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits

On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression

Amortized Bayesian Prototype Meta-learning: A New Probabilistic Meta-learning Approach to Few-shot Image Classification

Tractable contextual bandits beyond realizability

Learning User Preferences in Non-Stationary Environments

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

Efficient Statistics for Sparse Graphical Models from Truncated Samples

Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.

Feedback Coding for Active Learning

Shadow Manifold Hamiltonian Monte Carlo

Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms

Identification of Matrix Joint Block Diagonalization

A Variational Information Bottleneck Approach to Multi-Omics Data Integration

On the Privacy Properties of GAN-generated Samples

Multitask Bandit Learning Through Heterogeneous Feedback Aggregation

Independent Innovation Analysis for Nonlinear Vector Autoregressive Process

Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers

Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning

Q-learning with Logarithmic Regret

Communication Efficient Primal-Dual Algorithm for Nonconvex Nonsmooth Distributed Optimization

Robust and Private Learning of Halfspaces

Minimax Model Learning

On the Faster Alternating Least-Squares for CCA

Exploiting Equality Constraints in Causal Inference

Collaborative Classification from Noisy Labels

Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability Estimation

Maximizing Agreements for Ranking, Clustering and Hierarchical Clustering via MAX-CUT

Why did the distribution change?

Non-Volume Preserving Hamiltonian Monte Carlo and No-U-TurnSamplers

Iterative regularization for convex regularizers

Competing AI: How does competition feedback affect machine learning?

Stability and Risk Bounds of Iterative Hard Thresholding

On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow

Improved Complexity Bounds in Wasserstein Barycenter Problem

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond

All of the Fairness for Edge Prediction with Optimal Transport

γ-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator

Understanding and Mitigating Exploding Inverses in Invertible Neural Networks

Online probabilistic label trees

Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms

DP-MERF: Differentially Private Mean Embeddings with RandomFeatures for Practical Privacy-preserving Data Generation

Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings

Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations

Free-rider Attacks on Model Aggregation in Federated Learning

Reinforcement Learning in Parametric MDPs with Exponential Families

Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery

No-regret Algorithms for Multi-task Bayesian Optimization

Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization

CONTRA: Contrarian statistics for controlled variable selection

Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning

PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming

Adaptive wavelet pooling for convolutional neural networks

The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domain

Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features

High-Dimensional Multi-Task Averaging and Application to Kernel Mean Embedding

Gradient Descent in RKHS with Importance Labeling

Learning with Gradient Descent and Weakly Convex Losses

Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders

Approximate Data Deletion from Machine Learning Models

Budgeted and Non-Budgeted Causal Bandits

Stability and Differential Privacy of Stochastic Gradient Descent for Pairwise Learning with Non-Smooth Loss

Equitable and Optimal Transport with Multiple Agents

A Variational Inference Approach to Learning Multivariate Wold Processes

Active Online Learning with Hidden Shifting Domains

No-Regret Algorithms for Private Gaussian Process Bandit Optimization

The Teaching Dimension of Kernel Perceptron

Localizing Changes in High-Dimensional Regression Models

Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference

Corralling Stochastic Bandit Algorithms

Learning Matching Representations for Individualized Organ Transplantation Allocation

Misspecification in Prediction Problems and Robustness via Improper Learning

Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization

Selective Classification via One-Sided Prediction

Distributionally Robust Optimization for Deep Kernel Multiple Instance Learning

vqSGD: Vector Quantized Stochastic Gradient Descent

Smooth Bandit Optimization: Generalization to Holder Space

List Learning with Attribute Noise

High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation

Fractional moment-preserving initialization schemes for training deep neural networks

Inductive Mutual Information Estimation: A Convex Maximum-Entropy Copula Approach

Federated f-Differential Privacy

Implicit Regularization via Neural Feature Alignment

Aggregating Incomplete and Noisy Rankings

Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models

Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent

Differentiable Causal Discovery Under Unmeasured Confounding

The Sample Complexity of Meta Sparse Regression

A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

Group testing for connected communities

Federated Learning with Compression: Unified Analysis and Sharp Guarantees

Variational Autoencoder with Learned Latent Structure

RankDistil: Knowledge Distillation for Ranking

Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data

On the Linear Convergence of Policy Gradient Methods for Finite MDPs

Learning the Truth From Only One Side of the Story

Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples

Bayesian Inference with Certifiable Adversarial Robustness

Hierarchical Clustering in General Metric Spaces using Approximate Nearest Neighbors

Statistical Guarantees for Transformation Based Models with applications to Implicit Variational Inference

Reinforcement Learning for Mean Field Games with Strategic Complementarities

Cluster Trellis: Data Structures & Algorithms for Exact Inference in Hierarchical Clustering

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?

On the Consistency of Metric and Non-Metric K-Medoids

Non-Stationary Off-Policy Optimization

Efficient Interpolation of Density Estimators

A Statistical Perspective on Coreset Density Estimation

Shuffled Model of Differential Privacy in Federated Learning

Designing Transportable Experiments Under S-admissability

A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets

Private optimization without constraint violations

Direct Loss Minimization for Sparse Gaussian Processes

Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning

Linear Models are Robust Optimal Under Strategic Behavior

Matérn Gaussian Processes on Graphs

Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs

Evaluating Model Robustness and Stability to Dataset Shift

Continuum-Armed Bandits: A Function Space Perspective

Regret-Optimal Filtering

Evading the Curse of Dimensionality in Unconstrained Private GLMs

One-Sketch-for-All: Non-linear Random Features from Compressed Linear Measurements

Reinforcement Learning for Constrained Markov Decision Processes

Principal Component Regression with Semirandom Observations via Matrix Completion

Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum

Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration

Sample Elicitation

Random Coordinate Underdamped Langevin Monte Carlo

Variational inference for nonlinear ordinary differential equations

Approximation Algorithms for Orthogonal Non-negative Matrix Factorization

Fast Adaptation with Linearized Neural Networks

Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization

A Change of Variables Method For Rectangular Matrix-Vector Products

Provably Eﬃcient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case

Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective

Causal Inference with Selectively Deconfounded Data

Animal pose estimation from video data with a hierarchical von Mises-Fisher-Gaussian model

Mirror Descent View for Neural Network Quantization

Power of Hints for Online Learning with Movement Costs

Stochastic Bandits with Linear Constraints

Significance of Gradient Information in Bayesian Optimization

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

DAG-Structured Clustering by Nearest Neighbors

Follow Your Star: New Frameworks for Online Stochastic Matching with Known and Unknown Patience

Location Trace Privacy Under Conditional Priors

An Optimal Reduction of TV-Denoising to Adaptive Online Learning

Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints

Federated Multi-armed Bandits with Personalization

Hierarchical Inducing Point Gaussian Process for Inter-domian Observations

Fast Statistical Leverage Score Approximation in Kernel Ridge Regression

Learning Complexity of Simulated Annealing

Associative Convolutional Layers

Large Scale K-Median Clustering for Stable Clustering Instances

Couplings for Multinomial Hamiltonian Monte Carlo

Logistic Q-Learning

Clustering multilayer graphs with missing nodes

CLAR: Contrastive Learning of Auditory Representations

On the Effect of Auxiliary Tasks on Representation Dynamics

LassoNet: Neural Networks with Feature Sparsity

Projection-Free Optimization on Uniformly Convex Sets

Differentiable Greedy Algorithm for Monotone Submodular Maximization: Guarantees, Gradient Estimators, and Applications

Graphical Normalizing Flows

One-Round Communication Efficient Distributed M-Estimation

Regularized Policies are Reward Robust

Semi-Supervised Learning with Meta-Gradient

On Information Gain and Regret Bounds in Gaussian Process Bandits

On the proliferation of support vectors in high dimensions

A Fast and Robust Method for Global Topological Functional Optimization

Regression Discontinuity Design under Self-selection

Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns

When OT meets MoM: Robust estimation of Wasserstein Distance

Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint

False Discovery Rates in Biological Networks

Fourier Bases for Solving Permutation Puzzles

Accelerating Metropolis-Hastings with Lightweight Inference Compilation

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

Fully Gap-Dependent Bounds for Multinomial Logit Bandit

Alternating Direction Method of Multipliers for Quantization

Online Forgetting Process for Linear Regression Models

A Bayesian nonparametric approach to count-min sketch under power-law data streams

Nonlinear Functional Output Regression: A Dictionary Approach

When MAML Can Adapt Fast and How to Assist When It Cannot

Learning Smooth and Fair Representations

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification

Contextual Blocking Bandits

Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic Approximation

A comparative study on sampling with replacement vs Poisson sampling in optimal subsampling

Robust Imitation Learning from Noisy Demonstrations

Online Active Model Selection for Pre-trained Classifiers

Online Sparse Reinforcement Learning

A Contraction Approach to Model-based Reinforcement Learning

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry

Benchmarking Simulation-Based Inference

Fisher Auto-Encoders

Deep Spectral Ranking

On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems

Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures

Approximate Message Passing with Spectral Initialization for Generalized Linear Models

Active Learning with Maximum Margin Sparse Gaussian Processes

A Stein Goodness-of-test for Exponential Random Graph Models

Approximating Lipschitz continuous functions with GroupSort neural networks

Learning GPLVM with arbitrary kernels using the unscented transformation

Low-Rank Generalized Linear Bandit Problems

On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions

Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm

On the Generalization Properties of Adversarial Training

Adversarially Robust Estimate and Risk Analysis in Linear Regression

Adaptive Approximate Policy Iteration

Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications

Foundations of Bayesian Learning from Synthetic Data

Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates

Hierarchical Clustering via Sketches and Hierarchical Correlation Clustering

Generalization Bounds for Stochastic Saddle Point Problems

Learning to Defend by Learning to Attack

A Deterministic Streaming Sketch for Ridge Regression

Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems

On the role of data in PAC-Bayes

Bandit algorithms: Letting go of logarithmic regret for statistical robustness

Geometrically Enriched Latent Spaces

Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting

Kernel regression in high dimensions: Refined analysis beyond double descent

Self-Concordant Analysis of Generalized Linear Bandits with Forgetting

Logical Team Q-learning: An approach towards factored policies in cooperative MARL

Automatic structured variational inference

Neural Enhanced Belief Propagation on Factor Graphs

Predictive Complexity Priors

Improving predictions of Bayesian neural nets via local linearization

Generalized Spectral Clustering via Gromov-Wasserstein Learning

Shapley Flow: A Graph-based Approach to Interpreting Model Predictions

Scalable Constrained Bayesian Optimization

Sample efficient learning of image-based diagnostic classifiers via probabilistic labels

Nonparametric Variable Screening with Optimal Decision Stumps

Sharp Analysis of a Simple Model for Random Forests

An Analysis of the Adaptation Speed of Causal Models

Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints

Efficient Computation and Analysis of Distributional Shapley Values

A constrained risk inequality for general losses

Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms

Learning Prediction Intervals for Regression: Generalization and Calibration

Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network

Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

Multi-Fidelity High-Order Gaussian Processes for Physical Simulation

Deep Fourier Kernel for Self-Attentive Point Processes

Robustness and scalability under heavy tails, without strong convexity

Provable Hierarchical Imitation Learning via EM

Learning with risk-averse feedback under potentially heavy tails

Parametric Programming Approach for More Powerful and General Lasso Selective Inference

On the High Accuracy Limitation of Adaptive Property Estimation

Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers

Counterfactual Representation Learning with Balancing Weights

Influence Decompositions For Neural Network Attribution

Understanding the wiring evolution in differentiable neural architecture search

Understanding Gradient Clipping In Incremental Gradient Methods

Taming heavy-tailed features by shrinkage

Learning Contact Dynamics using Physically Structured Neural Networks

Unconstrained MAP Inference, Exponentiated Determinantal Point Processes, and Exponential Inapproximability

Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors

Explicit Regularization of Stochastic Gradient Methods through Duality

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

Moment-Based Variational Inference for Stochastic Differential Equations

A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks

Stochastic Gradient Descent Meets Distribution Regression

When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence

On the Suboptimality of Negative Momentum for Minimax Optimization

Context-Specific Likelihood Weighting

Minimal enumeration of all possible total effects in a Markov equivalence class

Predictive Power of Nearest Neighbors Algorithm under Random Perturbation

Nested Barycentric Coordinate System as an Explicit Feature Map

CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices

Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes

Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge Regression

Robust hypothesis testing and distribution estimation in Hellinger distance

Faster Kernel Interpolation for Gaussian Processes

SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups

Detection and Defense of Topological Adversarial Attacks on Graphs

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

Multi-Armed Bandits with Cost Subsidy

Causal Modeling with Stochastic Confounders

The Multiple Instance Learning Gaussian Process Probit Model

Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances

Meta Learning in the Continuous Time Limit

Fast and Smooth Interpolation on Wasserstein Space

Efficient Balanced Treatment Assignments for Experimentation

Tensor Networks for Probabilistic Sequence Modeling

Experimental Design for Regret Minimization in Linear Bandits

DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks

Dynamic Cutset Networks

Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Kernel Interpolation for Scalable Online Gaussian Processes

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

Contrastive learning of strong-mixing continuous-time stochastic processes

TenIPS: Inverse Propensity Sampling for Tensor Completion

Sketch based Memory for Neural Networks

Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge Regression

Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees

A Hybrid Approximation to the Marginal Likelihood

Prediction with Finitely many Errors Almost Surely

Density of States Estimation for Out of Distribution Detection

Product Manifold Learning

Automatic Differentiation Variational Inference with Mixtures

Fair for All: Best-effort Fairness Guarantees for Classification

Efficient Designs Of SLOPE Penalty Sequences In Finite Dimension

Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

Provably Efficient Safe Exploration via Primal-Dual Policy Optimization

Understanding Robustness in Teacher-Student Setting: A New Perspective

Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences

Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning

Online Model Selection for Reinforcement Learning with Function Approximation

Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits

Good Classifiers are Abundant in the Interpolating Regime

No-Regret Reinforcement Learning with Heavy-Tailed Rewards

A Spectral Analysis of Dot-product Kernels

Towards Flexible Device Participation in Federated Learning

Active Learning under Label Shift

Tracking Regret Bounds for Online Submodular Optimization

Offline detection of change-points in the mean for stationary graph signals.

Hyperbolic graph embedding with enhanced semi-implicit variational inference.

Rao-Blackwellised parallel MCMC

Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression

Calibrated Adaptive Probabilistic ODE Solvers

Online Robust Control of Nonlinear Systems with Large Uncertainty

Probabilistic Sequential Matrix Factorization

An Analysis of LIME for Text Data

Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-Information

Scalable Gaussian Process Variational Autoencoders

Causal Autoregressive Flows

Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models

A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

Spectral Tensor Train Parameterization of Deep Learning Layers

Local SGD: Unified Theory and New Efficient Methods

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders

The Base Measure Problem and its Solution

A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models

Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model

Sequential Random Sampling Revisited: Hidden Shuffle Method

Dirichlet Pruning for Convolutional Neural Networks

Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain

One-pass Stochastic Gradient Descent in overparametrized two-layer neural networks

On the Memory Mechanism of Tensor-Power Recurrent Models

Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits

Causal Inference under Networked Interference and Intervention Policy Enhancement

GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences

Latent Gaussian process with composite likelihoods and numerical quadrature

Deep Generative Missingness Pattern-Set Mixture Models

Minimax Estimation of Laplacian Constrained Precision Matrices

A Scalable Gradient Free Method for Bayesian Experimental Design with Implicit Models

Distribution Regression for Sequential Data

Direct-Search for a Class of Stochastic Min-Max Problems

Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry

Learning Temporal Point Processes with Intermittent Observations

On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity

Robust Learning under Strong Noise via SQs

Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models

Convergence Properties of Stochastic Hypergradients

Entropy Partial Transport with Tree Metrics: Theory and Practice

Combinatorial Gaussian Process Bandits with Probabilistically Triggered Arms

Differentiable Divergences Between Time Series

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Differentiating the Value Function by using Convex Duality

Rate-Regularization and Generalization in Variational Autoencoders

Asymptotics of Ridge(less) Regression under General Source Condition

Longitudinal Variational Autoencoder

An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte Carlo

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Learning Shared Subgraphs in Ising Model Pairs

Faster & More Reliable Tuning of Neural Networks: Bayesian Optimization with Importance Sampling

Bayesian Active Learning by Soft Mean Objective Cost of Uncertainty

Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization

Improved Exploration in Factored Average-Reward MDPs

Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries

Regularized ERM on random subspaces

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Meta-Learning Divergences for Variational Inference

Hidden Cost of Randomized Smoothing

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Improving Classifier Confidence using Lossy Label-Invariant Transformations

Graph Gamma Process Linear Dynamical Systems

Does Invariant Risk Minimization Capture Invariance?

A unified view of likelihood ratio and reparameterization gradients

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

CADA: Communication-Adaptive Distributed Adam

Principal Subspace Estimation Under Information Diffusion

Training a Single Bandit Arm

Flow-based Alignment Approaches for Probability Measures in Different Spaces

Model updating after interventions paradoxically introduces bias

Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and Algorithms

Gaming Helps! Learning from Strategic Interactions in Natural Dynamics

Differentially Private Weighted Sampling

Optimal query complexity for private sequential learning against eavesdropping

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions

The Sample Complexity of Level Set Approximation

Quantum Tensor Networks, Stochastic Processes, and Weighted Automata

Revisiting Projection-free Online Learning: the Strongly Convex Case

An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling

Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation

Wasserstein Random Forests and Applications in Heterogeneous Treatment Effects

Curriculum Learning by Optimizing Learning Dynamics

Learning Bijective Feature Maps for Linear ICA

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization

Sparse Algorithms for Markovian Gaussian Processes

Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning

On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent Variable Models

Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions