AISTATS 2022

492 papers

CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks

Ana Lucic, Maartje A. Ter Hoeve, Gabriele Tolomei, Maarten de Rijke, Fabrizio Silvestri

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints

Adil SALIM, Laurent Condat, Dmitry Kovalev, Peter Richtarik

Point Cloud Generation with Continuous Conditioning

Larissa T. Triess, Andre Bühler, David Peter, Fabian B. Flohr, Marius Zöllner

Projection Predictive Inference for Generalized Linear and Additive Multilevel Models

Alejandro Catalina, Paul-Christian Bürkner, Aki Vehtari

Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness

Beomsu Kim, Junghoon Seo

Independent Natural Policy Gradient always converges in Markov Potential Games

Roy Fox, Stephen M. Mcaleer, Will Overman, Ioannis Panageas

On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity

Khang Le, Huy Nguyen, Khai Nguyen, Tung Pham, nhật Hồ

Offline Policy Selection under Uncertainty

Mengjiao Yang, Bo Dai, Ofir Nachum, George Tucker, Dale Schuurmans

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

Jungtaek Kim, Seungjin Choi

Optimal partition recovery in general graphs

Yi Yu, Oscar Madrid, Alessandro Rinaldo

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

Fan Wang, Oscar Madrid, Yi Yu, Alessandro Rinaldo

Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization

Kiran K. Thekumparampil, Niao He, Sewoong Oh

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

Jiafan He, Dongruo Zhou, Quanquan Gu

Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes

Zhiyuan Jerry Lin, Raul Astudillo, Peter Frazier, Eytan Bakshy

Model-free Policy Learning with Reward Gradients

Qingfeng Lan, Samuele Tosatto, Homayoon Farrahi, Rupam Mahmood

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

Jiaye Teng, Weiran Huang, Haowei He

Learning a Single Neuron for Non-monotonic Activation Functions

Lei Wu

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

Yao Zhang, Jeroen Berrevoets, Mihaela van der Schaar

On the Generalization of Representations in Reinforcement Learning

Charline Le Lan, Stephen Tu, Adam Oberman, Rishabh Agarwal, Marc G. Bellemare

Gap-Dependent Unsupervised Exploration for Reinforcement Learning

Jingfeng Wu, Vladimir braverman, Lin Yang

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

Shivam Garg, Santosh Vempala

Privacy Amplification by Subsampling in Time Domain

Tatsuki Koga, Casey Meehan, Kamalika Chaudhuri

Mitigating Bias in Calibration Error Estimation

Rebecca Roelofs, Nicholas Cain, Jonathon Shlens, Michael C. Mozer

How to Learn when Data Gradually Reacts to Your Model

Zachary Izzo, James Zou, Lexing Ying

MLDemon:Deployment Monitoring for Machine Learning Systems

Tony Ginart, Martin Jinye Zhang, James Zou

Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent

Tongzheng Ren, Fuheng Cui, Alexia Atsidakou, Sujay Sanghavi, nhật Hồ

On Facility Location Problem in the Local Differential Privacy Model

Vincent Cohen-Addad, Yunus Esencayi, Chenglin Fan, Marco Gaboradi, Shi Li

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

Yue Wu, Dongruo Zhou, Quanquan Gu

Flexible Accuracy for Differential Privacy

Aman Bansal, Rahul Chunduru, Deepesh Data, Manoj Prabhakaran

An Information-Theoretic Justification for Model Pruning

Berivan Isik, Tsachy Weissman, Albert No

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

Xuhui Zhang, Jose Blanchet, Soumyadip Ghosh, Mark S. Squillante

Computing D-Stationary Points of $ρ$-Margin Loss SVM

Lai Tian, Anthony Man-Cho So

Momentum Accelerates the Convergence of Stochastic AUPRC Maximization

Guanghui Wang, Ming Yang, Lijun Zhang, Tianbao Yang

A Spectral Perspective of DNN Robustness to Label Noise

Oshrat Bar, Amnon Drory, Raja Giryes

On Margins and Derandomisation in PAC-Bayes

Felix Biggs, Benjamin Guedj

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

Kaiwen Zhou, Lai Tian, Anthony Man-Cho So, James Cheng

Certifiably Robust Variational Autoencoders

Ben Barrett, Alexander Camuto, Matthew Willetts, Tom Rainforth

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

Yirui Liu, Xinghao Qiao, Jessica Lam

Deep Neyman-Scott Processes

Chengkuan Hong, Christian Shelton

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

Jiajing Zheng, Alexander D’Amour, Alexander Franks

Federated Learning with Buffered Asynchronous Aggregation

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Mike Rabbat

Minimax Optimization: The Case of Convex-Submodular

Arman Adibi, Aryan Mokhtari, Hamed Hassani

Last Layer Marginal Likelihood for Invariance Learning

Pola Schwöbel, Martin Jørgensen, Sebastian W. Ober, Mark van der Wilk

Finding Nearly Everything within Random Binary Networks

Kartik Sreenivasan, Shashank Rajput, Jy-yong Sohn, Dimitris Papailiopoulos

Sinkformers: Transformers with Doubly Stochastic Attention

Michael E. Sander, Pierre Ablin, Mathieu Blondel, Gabriel Peyré

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

Tin D. Nguyen, Brian L. Trippe, Tamara Broderick

Spectral Pruning for Recurrent Neural Networks

Takashi Furuya, Kazuma Suetake, Koichi Taniguchi, Hiroyuki Kusumoto, Ryuji Saiin

A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions

Ben Adlam, Jake A. Levinson, Jeffrey Pennington

LIMESegment: Meaningful, Realistic Time Series Explanations

Torty Sivill, Peter Flach

Pairwise Fairness for Ordinal Regression

Matthäus Kleindessner, Samira Samadi, Muhammad Bilal Zafar, Krishnaram Kenthapadi, Chris Russell

A general sample complexity analysis of vanilla policy gradient

Rui Yuan, Robert M. Gower, Alessandro Lazaric

Measuring the robustness of Gaussian processes to kernel choice

William T. Stephenson, Soumya Ghosh, Tin D. Nguyen, Mikhail Yurochkin, Sameer Deshpande

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

Honghao Wei, Xin Liu, Lei Ying

Differentially Private Regression with Unbounded Covariates

Jason Milionis, Alkis Kalavasis, Dimitris Fotakis, Stratis Ioannidis

Learning Quantile Functions for Temporal Point Processes with Recurrent Neural Splines

Souhaib Ben Taieb

Nonstationary multi-output Gaussian processes via harmonizable spectral mixtures

Matias Altamirano, Felipe Tobar

Reward-Free Policy Space Compression for Reinforcement Learning

Mirco Mutti, Stefano Del Col, Marcello Restelli

State Dependent Performative Prediction with Stochastic Approximation

Qiang Li, Hoi-To Wai

Embedded Ensembles: infinite width limit and operating regimes

Maksim Velikanov, Roman V. Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov

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

Matti Karppa, Martin Aumüller, Rasmus Pagh

Random Effect Bandits

Rong Zhu, Branislav Kveton

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

Alexander Bartler, Andre Bühler, Felix Wiewel, Mario Döbler, Bin Yang

On PAC-Bayesian reconstruction guarantees for VAEs

Badr-Eddine Chérief-Abdellatif, Yuyang Shi, Arnaud Doucet, Benjamin Guedj

Super-Acceleration with Cyclical Step-sizes

Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien B. Taylor, Fabian Pedregosa

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

Lukas Fromme, Jasmina Bogojeska, Jonas Kuhn

Generative Models as Distributions of Functions

Emilien Dupont, Yee Whye Teh, Arnaud Doucet

Aligned Multi-Task Gaussian Process

Olga Mikheeva, Ieva Kazlauskaite, Adam Hartshorne, Hedvig Kjellström, Carl Henrik Ek

Randomized Stochastic Gradient Descent Ascent

Othmane Sebbouh, Marco Cuturi, Gabriel Peyré

Fast Rank-1 NMF for Missing Data with KL Divergence

Kazu Ghalamkari, Mahito Sugiyama

Metalearning Linear Bandits by Prior Update

Amit Peleg, Naama Pearl, Ron Meir

Uncertainty Quantification for Bayesian Optimization

Rui Tuo, Wenjia Wang

Sampling from Arbitrary Functions via PSD Models

Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi

Robust Deep Learning from Crowds with Belief Propagation

Hoyoung Kim, Seunghyuk Cho, Dongwoo Kim, Jungseul Ok

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

Tianyi Liu, Yan Li, Enlu Zhou, Tuo Zhao

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

Hajime Ono, Kazuhiro Minami, Hideitsu Hino

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

Yulai Zhao, Yuandong Tian, Jason Lee, Simon Du

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

Oliver E. Richardson

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

Jiawei Huang, Nan Jiang

An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski

Pairwise Supervision Can Provably Elicit a Decision Boundary

Han Bao, Takuya Shimada, Liyuan Xu, Issei Sato, Masashi Sugiyama

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Completion

Tian Tong, Cong Ma, Ashley Prater-Bennette, Erin Tripp, Yuejie Chi

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

Jihun Yun, Aurélie Lozano, Eunho Yang

Density Ratio Estimation via Infinitesimal Classification

Kristy Choi, Chenlin Meng, Yang Song, Stefano Ermon

Encrypted Linear Contextual Bandit

Evrard Garcelon, Matteo Pirotta, Vianney Perchet

Strategic ranking

Lydia T. Liu, Nikhil Garg, Christian Borgs

A Single-Timescale Method for Stochastic Bilevel Optimization

Tianyi Chen, Yuejiao Sun, Quan Xiao, Wotao Yin

Accurate Shapley Values for explaining tree-based models

Salim I. Amoukou, Tangi Salaün, Nicolas Brunel

Safe Optimal Design with Applications in Off-Policy Learning

Ruihao Zhu, Branislav Kveton

Confident Least Square Value Iteration with Local Access to a Simulator

Botao Hao, Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvári

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

Adrian Rivera Cardoso, Ryan Rogers

Unifying Importance Based Regularisation Methods for Continual Learning

Frederik Benzing

Moment Matching Deep Contrastive Latent Variable Models

Ethan Weinberger, Nicasia Beebe-Wang, Su-in Lee

Leveraging Time Irreversibility with Order-Contrastive Pre-training

Monica N. Agrawal, Hunter Lang, Michael Offin, Lior Gazit, David Sontag

Conditionally Gaussian PAC-Bayes

Eugenio Clerico, George Deligiannidis, Arnaud Doucet

Bayesian Classifier Fusion with an Explicit Model of Correlation

Susanne Trick, Constantin Rothkopf

Learning Inconsistent Preferences with Gaussian Processes

Siu Lun Chau, Javier Gonzalez, Dino Sejdinovic

Rejection sampling from shape-constrained distributions in sublinear time

Sinho Chewi, Patrik R. Gerber, Chen Lu, Thibaut Le Gouic, Philippe Rigollet

Efficient Algorithms for Extreme Bandits

Dorian Baudry, Yoan Russac, Emilie Kaufmann

Conditional Gradients for the Approximately Vanishing Ideal

Elias S. Wirth, Sebastian Pokutta

Improving Attribution Methods by Learning Submodular Functions

Piyushi Manupriya, Tarun Ram Menta, Sakethanath N. Jagarlapudi, Vineeth N. Balasubramanian