AISTATS 2022

492 papers

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

Robin Vandaele, Bo Kang, Tijl De Bie, Yvan Saeys

Dimensionality Reduction and Prioritized Exploration for Policy Search

Marius Memmel, Puze Liu, Davide Tateo, Jan Peters

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

Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou

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

Alexander Munteanu, Simon Omlor, Christian Peters

Improved analysis of randomized SVD for top-eigenvector approximation

Ruo-Chun Tzeng, Po-An Wang, Florian Adriaens, Aristides Gionis, Chi-Jen Lu

Nonstochastic Bandits and Experts with Arm-Dependent Delays

Dirk van der Hoeven, Nicolò Cesa-bianchi

Grassmann Stein Variational Gradient Descent

Xing Liu, Harrison Zhu, Jean-Francois Ton, George Wynne, Andrew Duncan

Bias-Variance Decompositions for Margin Losses

Danny Wood, Tingting Mu, Gavin Brown

Feature screening with kernel knockoffs

Benjamin Poignard, Peter J. Naylor, Héctor Climente-González, Makoto Yamada

On the Global Optimum Convergence of Momentum-based Policy Gradient

Yuhao Ding, Junzi Zhang, Javad Lavaei

A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization

Donghao Ying, Yuhao Ding, Javad Lavaei

Spectral risk-based learning using unbounded losses

Matthew J. Holland, El Mehdi Haress

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

Kentaro Kanamori, Takuya Takagi, Ken Kobayashi, Yuichi Ike

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

Dheeraj Baby, Yu-Xiang Wang

Parallel MCMC Without Embarrassing Failures

Daniel A. De Souza, Diego Mesquita, Samuel Kaski, Luigi Acerbi

A Bayesian Model for Online Activity Sample Sizes

Thomas S. Richardson, Yu Liu, James McQueen, Doug Hains

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

Lisha Chen, Tianyi Chen

Online Learning for Unknown Partially Observable MDPs

Mehdi Jafarnia Jahromi, Rahul Jain, Ashutosh Nayyar

Deep Multi-Fidelity Active Learning of High-Dimensional Outputs

Shibo Li, Zheng Wang, Robert Kirby, Shandian Zhe

Policy Learning for Optimal Individualized Dose Intervals

Guanhua Chen, Xiaomao Li, Menggang Yu

Online Page Migration with ML Advice

Piotr Indyk, Frederik Mallmann-Trenn, Slobodan Mitrovic, Ronitt Rubinfeld

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

Cristian I. Challu, Peihong Jiang, Ying Nian Wu, Laurent Callot

Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport

Alex Delalande

Parametric Bootstrap for Differentially Private Confidence Intervals

Cecilia Ferrando, Shufan Wang, Daniel Sheldon

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

Wenkai Xu

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

Youming Tao, Yulian Wu, Peng Zhao, Di Wang

Equivariance Discovery by Learned Parameter-Sharing

Raymond A. Yeh, Yuan-Ting Hu, Mark Hasegawa-Johnson, Alexander Schwing

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

Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike Von Luxburg

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

Chih-Kuan Yeh, Kuan-Yun Lee, Frederick Liu, Pradeep Ravikumar

A Complete Characterisation of ReLU-Invariant Distributions

Jan Macdonald, Stephan Wäldchen

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

Vlad Winter, Or Dinari, Oren Freifeld

Sample-and-threshold differential privacy: Histograms and applications

Graham Cormode, Akash Bharadwaj

A Witness Two-Sample Test

Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf, Krikamol Muandet

Implicitly Regularized RL with Implicit Q-values

Nino Vieillard, Marcin Andrychowicz, Anton Raichuk, Olivier Pietquin, Matthieu Geist

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

Randy Ardywibowo, Shahin Boluki, Zhangyang Wang, Bobak J. Mortazavi, Shuai Huang

Robust Probabilistic Time Series Forecasting

TaeHo Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang

A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows

Pedro Cisneros-Velarde, Francesco Bullo

Spiked Covariance Estimation from Modulo-Reduced Measurements

Elad Romanov, Or Ordentlich

On Distributionally Robust Optimization and Data Rebalancing

Agnieszka Słowik, Léon Bottou

Heavy-tailed Streaming Statistical Estimation

Che-Ping Tsai, Adarsh Prasad, Sivaraman Balakrishnan, Pradeep Ravikumar

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

Yaodong Yu, Tianyi Lin, Eric V. Mazumdar, Michael Jordan

Physics Informed Deep Kernel Learning

Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

Survival regression with proper scoring rules and monotonic neural networks

David Rindt, Robert Hu, David Steinsaltz, Dino Sejdinovic

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

Vivek Farias, Andrew A. Li, Tianyi Peng

Towards Return Parity in Markov Decision Processes

Jianfeng Chi, Jian Shen, Xinyi Dai, Weinan Zhang, Yuan Tian

k-Pareto Optimality-Based Sorting with Maximization of Choice

Jean Ruppert, Marharyta Aleksandrova, Thomas Engel

Fixed Support Tree-Sliced Wasserstein Barycenter

Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada

Multiway Spherical Clustering via Degree-Corrected Tensor Block Models

Jiaxin Hu, Miaoyan Wang

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

Nghia Hoang, Anoop Deoras, Tong Zhao, Jin Li, George Karypis

Policy Learning and Evaluation with Randomized Quasi-Monte Carlo

Sébastien M. R. Arnold, Pierre L’Ecuyer, Liyu Chen, Yi-Fan Chen, Fei Sha

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

Anas Barakat, Pascal Bianchi, Julien Lehmann

A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits

Pierre Laforgue, Giulia Clerici, Nicolò Cesa-bianchi, Ran Gilad-Bachrach

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

Charita Dellaporta, Jeremias Knoblauch, Theodoros Damoulas, François-Xavier Briol

Robustness and Reliability When Training With Noisy Labels

Amanda Olmin, Fredrik Lindsten

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

nhật Hồ, Tianyi Lin, Michael Jordan

Variational Marginal Particle Filters

Jinlin Lai, Justin Domke, Daniel Sheldon

Adaptively Partitioning Max-Affine Estimators for Convex Regression

Gabor Balazs

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

Youssef Diouane, Aurelien Lucchi, Vihang Prakash Patil

Sampling in Dirichlet Process Mixture Models for Clustering Streaming Data

Or Dinari, Oren Freifeld

Identity Testing of Reversible Markov Chains

Sela Fried, Geoﬀrey Wolfer

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

Anirban Santara, Gaurav Aggarwal, Shuai Li, Claudio Gentile

Causally motivated shortcut removal using auxiliary labels

Maggie Makar, Ben Packer, Dan Moldovan, Davis Blalock, Yoni Halpern

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations

Winnie Xu, Ricky T. Q. Chen, Xuechen Li, David Duvenaud

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

Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtarik

Marginalized Operators for Off-policy Reinforcement Learning

Yunhao Tang, Mark Rowland, Rémi Munos, Michal Valko

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

Kevin Bello, Chuyang Ke, Jean Honorio

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

Nicholas Krämer, Jonathan Schmidt, Philipp Hennig

Distributed Sparse Multicategory Discriminant Analysis

Hengchao Chen, Qiang Sun

Obtaining Causal Information by Merging Datasets with MAXENT

Sergio H. Garrido Mejia, Elke Kirschbaum, Dominik Janzing

Jointly Efficient and Optimal Algorithms for Logistic Bandits

Louis Faury, Marc Abeille, Kwang-Sung Jun, Clément Calauzènes

Being a Bit Frequentist Improves Bayesian Neural Networks

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

Finding Dynamics Preserving Adversarial Winning Tickets

Xupeng Shi, Pengfei Zheng, A. Adam Ding, Yuan Gao, Weizhong Zhang

Exploring Image Regions Not Well Encoded by an INN

Zenan Ling, Fan Zhou, Meng Wei, Quanshi Zhang

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

Aadirupa Saha, Suprovat Ghoshal

Gap-Dependent Bounds for Two-Player Markov Games

Zehao Dou, Zhuoran Yang, Zhaoran Wang, Simon Du

Multi-armed Bandit Algorithm against Strategic Replication

Suho Shin, Seungjoon Lee, Jungseul Ok

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

Eduard Gorbunov, Nicolas Loizou, Gauthier Gidel

k-experts - Online Policies and Fundamental Limits

Samrat Mukhopadhyay, Sourav Sahoo, Abhishek Sinha

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

Baturalp Yalçın, Haixiang Zhang, Javad Lavaei, Somayeh Sojoudi

SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums

Jiabin Chen, Rui Yuan, Guillaume Garrigos, Robert M. Gower

Neural Contextual Bandits without Regret

Parnian Kassraie, Andreas Krause

Sequential Multivariate Change Detection with Calibrated and Memoryless False Detection Rates

Oliver Cobb, Arnaud Van Looveren, Janis Klaise

Deep Layer-wise Networks Have Closed-Form Weights

Chieh Tzu Wu, Aria Masoomi, Arthur Gretton, Jennifer Dy

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

Hyun-Suk Lee

Unlabeled Data Help: Minimax Analysis and Adversarial Robustness

Yue Xing, Qifan Song, Guang Cheng

Approximate Function Evaluation via Multi-Armed Bandits

Tavor Z. Baharav, Gary Cheng, Mert Pilanci, David Tse

Gaussian Process Bandit Optimization with Few Batches

Zihan Li, Jonathan Scarlett

Norm-Agnostic Linear Bandits

Spencer B. Gales, Sunder Sethuraman, Kwang-Sung Jun

Maillard Sampling: Boltzmann Exploration Done Optimally

Jie Bian, Kwang-Sung Jun

On Linear Model with Markov Signal Priors

Lan V. Truong

Federated Reinforcement Learning with Environment Heterogeneity

Hao Jin, Yang Peng, Wenhao Yang, Shusen Wang, Zhihua Zhang

Cross-Loss Influence Functions to Explain Deep Network Representations

Andrew Silva, Rohit Chopra, Matthew Gombolay