AISTATS 2022 Papers

Skip to yearly menu bar Skip to main content

Browse

mini compact topic detail

Federated Reinforcement Learning with Environment Heterogeneity

Maillard Sampling: Boltzmann Exploration Done Optimally

Gaussian Process Bandit Optimization with Few Batches

System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy

Deep Layer-wise Networks Have Closed-Form Weights

Sequential Multivariate Change Detection with Calibrated and Memoryless False Detection Rates

Neural Contextual Bandits without Regret

SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums

Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods

k-experts - Online Policies and Fundamental Limits

Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity

Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits

Finding Dynamics Preserving Adversarial Winning Tickets

Being a Bit Frequentist Improves Bayesian Neural Networks

Jointly Efficient and Optimal Algorithms for Logistic Bandits

Obtaining Causal Information by Merging Datasets with MAXENT

Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations

Causally motivated shortcut removal using auxiliary labels

Identity Testing of Reversible Markov Chains

Sampling in Dirichlet Process Mixture Models for Clustering Streaming Data

A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning

Robustness and Reliability When Training With Noisy Labels

Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap

A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits

Fixed Support Tree-Sliced Wasserstein Barycenter

k-Pareto Optimality-Based Sorting with Maximization of Choice

Survival regression with proper scoring rules and monotonic neural networks

Spiked Covariance Estimation from Modulo-Reduced Measurements

A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows

A Witness Two-Sample Test

Sample-and-threshold differential privacy: Histograms and applications

A Complete Characterisation of ReLU-Invariant Distributions

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference

Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection

Online Learning for Unknown Partially Observable MDPs

Convergence of Langevin Monte Carlo in Chi-Squared and Rényi Divergence

Learning from Multiple Noisy Partial Labelers

Controlling Epidemic Spread using Probabilistic Diffusion Models on Networks

Learning Tensor Representations for Meta-Learning

On a Connection Between Fast and Sparse Oblivious Subspace Embeddings

Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning

Generalised GPLVM with Stochastic Variational Inference

Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inference

Sensing Cox Processes via Posterior Sampling and Positive Bases

Transfer Learning with Gaussian Processes for Bayesian Optimization

Orthogonal Multi-Manifold Enriching of Directed Networks

Solving Marginal MAP Exactly by Probabilistic Circuit Transformations

Common Failure Modes of Subcluster-based Sampling in Dirichlet Process Gaussian Mixture Models - and a Deep-learning Solution

How to Learn when Data Gradually Reacts to Your Model

Improved Approximation Algorithms for Individually Fair Clustering

Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm

Orbital MCMC

On Margins and Derandomisation in PAC-Bayes

Warping Layer: Representation Learning for Label Structures in Weakly Supervised Learning

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition

ExactBoost: Directly Boosting the Margin in Combinatorial and Non-decomposable Metrics

Two-Sample Test with Kernel Projected Wasserstein Distance

Cross-Loss Influence Functions to Explain Deep Network Representations

Adaptively Partitioning Max-Affine Estimators for Convex Regression

Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

Sinkformers: Transformers with Doubly Stochastic Attention

Many processors, little time: MCMC for partitions via optimal transport couplings

Convergence of online k-means

Best Arm Identification with Safety Constraints

Adaptive Importance Sampling meets Mirror Descent : a Bias-variance Tradeoff

Resampling Base Distributions of Normalizing Flows

On Coresets for Fair Regression and Individually Fair Clustering

Pairwise Fairness for Ordinal Regression

Fast Sparse Classification for Generalized Linear and Additive Models

DEANN: Speeding up Kernel-Density Estimation using Approximate Nearest Neighbor Search

Chernoff Sampling for Active Testing and Extension to Active Regression

Predicting the impact of treatments over time with uncertainty aware neural differential equations.

Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions

On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction

A prior-based approximate latent Riemannian metric

Outcome Assumptions and Duality Theory for Balancing Weights

Leveraging Time Irreversibility with Order-Contrastive Pre-training

Provable Continual Learning via Sketched Jacobian Approximations

FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning

The Curse of Passive Data Collection in Batch Reinforcement Learning

Relational Neural Markov Random Fields

Dropout as a Regularizer of Interaction Effects

Equivariant Deep Dynamical Model for Motion Prediction

Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time

Transductive Robust Learning Guarantees

Optimizing Early Warning Classifiers to Control False Alarms via a Minimum Precision Constraint

Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size

Differentiable Bayesian inference of SDE parameters using a pathwise series expansion of Brownian motion

Tight bounds for minimum $\ell_1$-norm interpolation of noisy data

PAC Learning of Quantum Measurement Classes : Sample Complexity Bounds and Universal Consistency

Policy Learning and Evaluation with Randomized Quasi-Monte Carlo

Learning to Plan Variable Length Sequences of Actions with a Cascading Bandit Click Model of User Feedback

Estimators of Entropy and Information via Inference in Probabilistic Models

Modeling Conditional Dependencies in Multiagent Trajectories

Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes

Physics Informed Deep Kernel Learning

Flexible Accuracy for Differential Privacy

Towards Understanding Biased Client Selection in Federated Learning

Exact Community Recovery over Signed Graphs

Learning Interpretable, Tree-Based Projection Mappings for Nonlinear Embeddings

Feature screening with kernel knockoffs

Learning Sparse Fixed-Structure Gaussian Bayesian Networks

A Unified View of SDP-based Neural Network Verification through Completely Positive Programming

Rapid Convergence of Informed Importance Tempering

Distributed Sparse Multicategory Discriminant Analysis

Asynchronous Distributed Optimization with Stochastic Delays

AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning

Generative Models as Distributions of Functions

Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective

Iterative Alignment Flows

Optimal estimation of Gaussian DAG models

Data-splitting improves statistical performance in overparameterized regimes

Firebolt: Weak Supervision Under Weaker Assumptions

A Dimensionality Reduction Method for Finding Least Favorable Priors with a Focus on Bregman Divergence

Zeroth-Order Methods for Convex-Concave Min-max Problems: Applications to Decision-Dependent Risk Minimization

Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization

On Some Fast And Robust Classifiers For High Dimension, Low Sample Size Data

New Coresets for Projective Clustering and Applications

An Unsupervised Hunt for Gravitational Lenses

An Alternate Policy Gradient Estimator for Softmax Policies

Efficient and passive learning of networked dynamical systems driven by non-white exogenous inputs

Label differential privacy via clustering

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Optimal transport with $f$-divergence regularization and generalized Sinkhorn algorithm

State Dependent Performative Prediction with Stochastic Approximation

On the Value of Prior in Online Learning to Rank

Using time-series privileged information for provably efficient learning of prediction models

Pareto Optimal Model Selection in Linear Bandits

Density Ratio Estimation via Infinitesimal Classification

Nuances in Margin Conditions Determine Gains in Active Learning

Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Meta Learning MDPs with linear transition models

Approximate Function Evaluation via Multi-Armed Bandits

Variational Marginal Particle Filters

A New Notion of Individually Fair Clustering: $\alpha$-Equitable $k$-Center

Variational Continual Proxy-Anchor for Deep Metric Learning

Conditional Linear Regression for Heterogeneous Covariances

Learning in Stochastic Monotone Games with Decision-Dependent Data

Sobolev Norm Learning Rates for Conditional Mean Embeddings

On the Convergence of Continuous Constrained Optimization for Structure Learning

TD-GEN: Graph Generation Using Tree Decomposition

Hierarchical Bayesian Bandits

Neural Enhanced Dynamic Message Passing

Random Effect Bandits

Synthsonic: Fast, Probabilistic modeling and Synthesis of Tabular Data

A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints

Optimal partition recovery in general graphs

Multi-class classification in nonparametric active learning

On the Generalization of Representations in Reinforcement Learning

Amortized Rejection Sampling in Universal Probabilistic Programming

A Class of Geometric Structures in Transfer Learning: Minimax Bounds and Optimality

Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning

Dimensionality Reduction and Prioritized Exploration for Policy Search

Optimal Compression of Locally Differentially Private Mechanisms

Differentially Private Regression with Unbounded Covariates

Proximal Optimal Transport Modeling of Population Dynamics

Strategic ranking

ContextGen: Targeted Data Generation for Low Resource Domain Specific Text Classification

Reconstructing Test Labels from Noisy Loss Functions

One-bit Submission for Locally Private Quasi-MLE: Its Asymptotic Normality and Limitation

Almost Optimal Universal Lower Bound for Learning Causal DAGs with Atomic Interventions

Improved analysis of randomized SVD for top-eigenvector approximation

Exploring Image Regions Not Well Encoded by an INN

Online Page Migration with ML Advice

Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity

Implicitly Regularized RL with Implicit Q-values

Equivariance Discovery by Learned Parameter-Sharing

On Distributionally Robust Optimization and Data Rebalancing

Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation

Solving Multi-Arm Bandit Using a Few Bits of Communication

Entropy Regularized Optimal Transport Independence Criterion

Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals

Top K Ranking for Multi-Armed Bandit with Noisy Evaluations

Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization

Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domains by Adaptive Discretization

Convex Analysis of the Mean Field Langevin Dynamics

Norm-Agnostic Linear Bandits

Standardisation-function Kernel Stein Discrepancy: A Unifying View on Kernel Stein Discrepancy Tests for Goodness-of-fit

SHAFF: Fast and consistent SHApley eFfect estimates via random Forests

Testing Granger Non-Causality in Panels with Cross-Sectional Dependencies

Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis

Mean Nyström Embeddings for Adaptive Compressive Learning

PAC Mode Estimation using PPR Martingale Confidence Sequences

Feature Collapsing for Gaussian Process Variable Ranking

The Curse Revisited: When are Distances Informative for the Ground Truth in Noisy High-Dimensional Data?

Gap-Dependent Bounds for Two-Player Markov Games

Accurate Shapley Values for explaining tree-based models

Node Feature Kernels Increase Graph Convolutional Network Robustness

Differentially Private Federated Learning on Heterogeneous Data

Fast Rank-1 NMF for Missing Data with KL Divergence

Heavy-tailed Streaming Statistical Estimation

Compressed Rule Ensemble Learning

CATVI: Conditional and Adaptively Truncated Variational Inference for Hierarchical Bayesian Nonparametric Models

Marginalized Operators for Off-policy Reinforcement Learning

An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization

On the Assumptions of Synthetic Control Methods

A Spectral Perspective of DNN Robustness to Label Noise

Lagrangian manifold Monte Carlo on Monge patches

Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?

Parallel MCMC Without Embarrassing Failures

Counterfactual Explanation Trees: Transparent and Consistent Actionable Recourse with Decision Trees

Spectral risk-based learning using unbounded losses

A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization

On the Global Optimum Convergence of Momentum-based Policy Gradient

Nonstochastic Bandits and Experts with Arm-Dependent Delays

p-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets

Non-stationary Online Learning with Memory and Non-stochastic Control

Improving Attribution Methods by Learning Submodular Functions

Conditional Gradients for the Approximately Vanishing Ideal

Efficient Algorithms for Extreme Bandits

Rejection sampling from shape-constrained distributions in sublinear time

Bayesian Classifier Fusion with an Explicit Model of Correlation

Conditionally Gaussian PAC-Bayes

Moment Matching Deep Contrastive Latent Variable Models

Unifying Importance Based Regularisation Methods for Continual Learning

Differentially Private Histograms under Continual Observation: Streaming Selection into the Unknown

Confident Least Square Value Iteration with Local Access to a Simulator

Safe Optimal Design with Applications in Off-Policy Learning

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Completion

Pairwise Supervision Can Provably Elicit a Decision Boundary

Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose Your Model, Not Your Loss Function

Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

Sampling from Arbitrary Functions via PSD Models

Uncertainty Quantification for Bayesian Optimization

Metalearning Linear Bandits by Prior Update

Randomized Stochastic Gradient Descent Ascent

Aligned Multi-Task Gaussian Process

Super-Acceleration with Cyclical Step-sizes

On PAC-Bayesian reconstruction guarantees for VAEs

MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption

Reward-Free Policy Space Compression for Reinforcement Learning

Learning Quantile Functions for Temporal Point Processes with Recurrent Neural Splines

Triple-Q: A Model-Free Algorithm for Constrained Reinforcement Learning with Sublinear Regret and Zero Constraint Violation

Measuring the robustness of Gaussian processes to kernel choice

A general sample complexity analysis of vanilla policy gradient

LIMESegment: Meaningful, Realistic Time Series Explanations

A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions

Spectral Pruning for Recurrent Neural Networks

Finding Nearly Everything within Random Binary Networks

Last Layer Marginal Likelihood for Invariance Learning

Minimax Optimization: The Case of Convex-Submodular

Federated Learning with Buffered Asynchronous Aggregation

Bayesian Inference and Partial Identification in Multi-Treatment Causal Inference with Unobserved Confounding

Deep Neyman-Scott Processes

Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums

Computing D-Stationary Points of $\rho$-Margin Loss SVM

An Information-Theoretic Justification for Model Pruning

Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

On Facility Location Problem in the Local Differential Privacy Model

Mitigating Bias in Calibration Error Estimation

How and When Random Feedback Works: A Case Study of Low-Rank Matrix Factorization

Gap-Dependent Unsupervised Exploration for Reinforcement Learning

Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects

Learning a Single Neuron for Non-monotonic Activation Functions

Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis

Model-free Policy Learning with Reward Gradients

Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs

Denoising and change point localisation in piecewise-constant high-dimensional regression coefficients

On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity

Independent Natural Policy Gradient always converges in Markov Potential Games

Projection Predictive Inference for Generalized Linear and Additive Multilevel Models

CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks

Safe Active Learning for Multi-Output Gaussian Processes

Variational Autoencoders: A Harmonic Perspective

On the Consistency of Max-Margin Losses

Learning Proposals for Practical Energy-Based Regression

Improved Algorithms for Misspecified Linear Markov Decision Processes

Optimal Accounting of Differential Privacy via Characteristic Function

Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets

Bayesian Link Prediction with Deep Graph Convolutional Gaussian Processes

On the Interplay between Information Loss and Operation Loss in Representations for Classification

Pulling back information geometry

Federated Myopic Community Detection with One-shot Communication

Variational Gaussian Processes: A Functional Analysis View

Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe

Off-Policy Risk Assessment for Markov Decision Processes

Kantorovich Mechanism for Pufferfish Privacy

Margin-distancing for safe model explanation

Modelling Non-Smooth Signals with Complex Spectral Structure

Convergent Working Set Algorithm for Lasso with Non-Convex Sparse Regularizers

Crowdsourcing Regression: A Spectral Approach

How to scale hyperparameters for quickshift image segmentation

Wide Mean-Field Bayesian Neural Networks Ignore the Data

Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems

Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE

Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms

Efficient Kernelized UCB for Contextual Bandits

Acceleration in Distributed Optimization under Similarity

Corruption-robust Offline Reinforcement Learning

A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learning

Harmless interpolation in regression and classification with structured features

Masked Training of Neural Networks with Partial Gradients

On Combining Bags to Better Learn from Label Proportions

Permutation Equivariant Layers for Higher Order Interactions

Parameter-Free Online Linear Optimization with Side Information via Universal Coin Betting

Performative Prediction in a Stateful World

Learning Revenue-Maximizing Auctions With Differentiable Matching

The Tree Loss: Improving Generalization with Many Classes

Double Control Variates for Gradient Estimation in Discrete Latent Variable Models

Learning Competitive Equilibria in Exchange Economies with Bandit Feedback

Differential privacy for symmetric log-concave mechanisms

Fair Disaster Containment via Graph-Cut Problems

QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning

Lifted Division for Lifted Hugin Belief Propagation

Are All Linear Regions Created Equal?

Co-Regularized Adversarial Learning for Multi-Domain Text Classification

Near Instance Optimal Model Selection for Pure Exploration Linear Bandits

Identification in Tree-shaped Linear Structural Causal Models

PAC Top-$k$ Identification under SST in Limited Rounds

Dual-Level Adaptive Information Filtering for Interactive Image Segmentation

A Predictive Approach to Bayesian Nonparametric Survival Analysis

On the equivalence of Oja's algorithm and GROUSE

Neural score matching for high-dimensional causal inference

Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks

Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning

Investigating the Role of Negatives in Contrastive Representation Learning

Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis

Cycle Consistent Probability Divergences Across Different Spaces

A Bandit Model for Human-Machine Decision Making with Private Information and Opacity

Approximate Top-$m$ Arm Identification with Heterogeneous Reward Variances

On perfectness in Gaussian graphical models

Nearly Optimal Algorithms for Level Set Estimation

Complex Momentum for Optimization in Games

Asymptotically Optimal Locally Private Heavy Hitters via Parameterized Sketches

Tuning-Free Generalized Hamiltonian Monte Carlo

Federated Functional Gradient Boosting

Stochastic Extragradient: General Analysis and Improved Rates

Deep Non-crossing Quantiles through the Partial Derivative

Vanishing Curvature in Randomly Initialized Deep ReLU Networks

Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes

Self-training Converts Weak Learners to Strong Learners in Mixture Models

Mode estimation on matrix manifolds: Convergence and robustness

Towards Federated Bayesian Network Structure Learning with Continuous Optimization

Hardness of Learning a Single Neuron with Adversarial Label Noise

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

A Bayesian Approach for Stochastic Continuum-armed Bandit with Long-term Constraints

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory

Look-Ahead Acquisition Functions for Bernoulli Level Set Estimation

Debiasing Samples from Online Learning Using Bootstrap

Contrasting the landscape of contrastive and non-contrastive learning

Fundamental limits for rank-one matrix estimation with groupwise heteroskedasticity

Decoupling Local and Global Representations of Time Series

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning

Online Continual Adaptation with Active Self-Training

Structured variational inference in Bayesian state-space models

Structured Multi-task Learning for Molecular Property Prediction

Nonparametric Relational Models with Superrectangulation

Regret, stability & fairness in matching markets with bandit learners

Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods

Near-Optimal Task Selection for Meta-Learning with Mutual Information and Online Variational Bayesian Unlearning

Sketch-and-lift: scalable subsampled semidefinite program for K-means clustering

Calibration Error for Heterogeneous Treatment Effects

Recoverability Landscape of Tree Structured Markov Random Fields under Symmetric Noise

Learning and Generalization in Overparameterized Normalizing Flows

Disentangling Whether from When in a Neural Mixture Cure Model for Failure Time Data

Sample Complexity of Robust Reinforcement Learning with a Generative Model

LocoProp: Enhancing BackProp via Local Loss Optimization

Primal-Dual Stochastic Mirror Descent for MDPs

Marginalising over Stationary Kernels with Bayesian Quadrature

Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics

Provable Adversarial Robustness for Fractional Lp Threat Models

Learning Pareto-Efficient Decisions with Confidence

Pick-and-Mix Information Operators for Probabilistic ODE Solvers

Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning

The Importance of Future Information in Credit Card Fraud Detection

A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits

Efficient computation of the the volume of a polytope in high-dimensions using Piecewise Deterministic Markov Processes

REPID: Regional Effect Plots with implicit Interaction Detection

Statistical Depth Functions for Ranking Distributions: Definitions, Statistical Learning and Applications

Duel-based Deep Learning system for solving IQ tests

Increasing the accuracy and resolution of precipitation forecasts using deep generative models

Multivariate Quantile Function Forecaster

Non-separable Spatio-temporal Graph Kernels via SPDEs

On the Oracle Complexity of Higher-Order Smooth Non-Convex Finite-Sum Optimization

Model-agnostic out-of-distribution detection using combined statistical tests

Generalized Group Testing

Adaptive A/B Test on Networks with Cluster Structures

Spectral Robustness for Correlation Clustering Reconstruction in Semi-Adversarial Models

Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge

Two-way Sparse Network Inference for Count Data

Quadric Hypersurface Intersection for Manifold Learning in Feature Space

Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons

Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach

Forward Looking Best-Response Multiplicative Weights Update Methods for Bilinear Zero-sum Games

Hypergraph Simultaneous Generators

Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation

Causal Effect Identification with Context-specific Independence Relations of Control Variables

Data Appraisal Without Data Sharing

A Manifold View of Adversarial Risk

Statistical and computational thresholds for the planted k-densest sub-hypergraph problem

The Fast Kernel Transform

A Bayesian Model for Online Activity Sample Sizes

Multi-armed Bandit Algorithm against Strategic Replication

Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits

Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates

Adversarially Robust Kernel Smoothing

Learning Inconsistent Preferences with Gaussian Processes

Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization

A Single-Timescale Method for Stochastic Bilevel Optimization

Robust Training in High Dimensions via Block Coordinate Geometric Median Descent

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL

PACm-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime

Thompson Sampling with a Mixture Prior

An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift

Differentially Private Densest Subgraph

Robust Probabilistic Time Series Forecasting

Efficient interventional distribution learning in the PAC framework

Optimal channel selection with discrete QCQP

Towards Return Parity in Markov Decision Processes

Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis

Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise

Towards an Understanding of Default Policies in Multitask Policy Optimization

Can we Generalize and Distribute Private Representation Learning?

Fast and accurate optimization on the orthogonal manifold without retraction

Laplacian Constrained Precision Matrix Estimation: Existence and High Dimensional Consistency

Conditionally Tractable Density Estimation using Neural Networks

Privacy Amplification by Subsampling in Time Domain

Certifiably Robust Variational Autoencoders

Online Competitive Influence Maximization

Weighted Gaussian Process Bandits for Non-stationary Environments

A general class of surrogate functions for stable and efficient reinforcement learning

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem

Second-Order Sensitivity Analysis for Bilevel Optimization

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms

Provable Lifelong Learning of Representations

Efficient Online Bayesian Inference for Neural Bandits

Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge

Privacy Amplification by Decentralization

Point Cloud Generation with Continuous Conditioning

Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness

Momentum Accelerates the Convergence of Stochastic AUPRC Maximization

Embedded Ensembles: infinite width limit and operating regimes

Encrypted Linear Contextual Bandit

Unlabeled Data Help: Minimax Analysis and Adversarial Robustness

Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation

Uncertainty Quantification for Low-Rank Matrix Completion with Heterogeneous and Sub-Exponential Noise

Estimating Functionals of the Out-of-Sample Error Distribution in High-Dimensional Ridge Regression

Effective Nonlinear Feature Selection Method based on HSIC Lasso and with Variational Inference

Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

GraphAdaMix: Enhancing Node Representations with Graph Adaptive Mixtures

MLDemon:Deployment Monitoring for Machine Learning Systems

Robust Deep Learning from Crowds with Belief Propagation

Bias-Variance Decompositions for Margin Losses

Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond

Policy Learning for Optimal Individualized Dose Intervals

Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations

Multiway Spherical Clustering via Degree-Corrected Tensor Block Models

Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits

Can Functional Transfer Methods Capture Simple Inductive Biases?

Offline Policy Selection under Uncertainty

Parametric Bootstrap for Differentially Private Confidence Intervals

On Linear Model with Markov Signal Priors

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

On Learning Mixture Models with Sparse Parameters

Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes

Fast Fourier Transform Reductions for Bayesian Network Inference

Predictive variational Bayesian inference as risk-seeking optimization

Stateful Offline Contextual Policy Evaluation and Learning

Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximations

Coresets for Data Discretization and Sine Wave Fitting

Online Control of the False Discovery Rate under “Decision Deadlines”

Doubly Mixed-Effects Gaussian Process Regression

Optimal Design of Stochastic DNA Synthesis Protocols based on Generative Sequence Models

Weak Separation in Mixture Models and Implications for Principal Stratification

Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent

Adaptive Multi-Goal Exploration

On Convergence of Lookahead in Smooth Games

Learning Personalized Item-to-Item Recommendation Metric via Implicit Feedback

On Uncertainty Estimation by Tree-based Surrogate Models in Sequential Model-based Optimization

Nonstationary multi-output Gaussian processes via harmonizable spectral mixtures

Deep Multi-Fidelity Active Learning of High-Dimensional Outputs

Diversity and Generalization in Neural Network Ensembles

Sample Complexity of Policy-Based Methods under Off-Policy Sampling and Linear Function Approximation

Minimal Expected Regret in Linear Quadratic Control

Particle-based Adversarial Local Distribution Regularization

Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression

Variance Minimization in the Wasserstein Space for Invariant Causal Prediction

Grassmann Stein Variational Gradient Descent

Fast Distributionally Robust Learning with Variance-Reduced Min-Max Optimization

Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport

On Structured Filtering-Clustering: Global Error Bound and Optimal First-Order Algorithms

A View of Exact Inference in Graphs from the Degree-4 Sum-of-Squares Hierarchy

The role of optimization geometry in single neuron learning

On Global-view Based Defense via Adversarial Attack and Defense Risk Guaranteed Bounds

On the complexity of the optimal transport problem with graph-structured cost