AISTATS 2022

492 papers

Doubly Mixed-Effects Gaussian Process Regression

Jun Ho Yoon, Daniel P. Jeong, Seyoung Kim

On the Value of Prior in Online Learning to Rank

Branislav Kveton, Ofer Meshi, Masrour Zoghi, Zhen Qin

Dual-Level Adaptive Information Filtering for Interactive Image Segmentation

Ervine Zheng, Qi Yu, Rui Li, Pengcheng Shi, Anne Haake

Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time

Yuyang Deng, Mohammad Mahdi Kamani, Mehrdad Mahdavi

PAC Top-k Identification under SST in Limited Rounds

Arpit Agarwal, Sanjeev Khanna, Prathamesh Patil

Pareto Optimal Model Selection in Linear Bandits

Yinglun Zhu, Robert Nowak

Identification in Tree-shaped Linear Structural Causal Models

Benito van der Zander, Marcel Wienöbst, Markus Bläser, Maciej Liśkiewicz

Near Instance Optimal Model Selection for Pure Exploration Linear Bandits

Yinglun Zhu, Julian Katz-Samuels, Robert Nowak

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

Chinmay Maheshwari, Chih-Yuan Chiu, Eric Mazumdar, Shankar Sastry, Lillian Ratliff

Co-Regularized Adversarial Learning for Multi-Domain Text Classification

Yuan Wu, Diana Inkpen, Ahmed El-Roby

An Alternate Policy Gradient Estimator for Softmax Policies

Shivam Garg, Samuele Tosatto, Yangchen Pan, Martha White, Rupam Mahmood

Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms

Joshua Agterberg, Jeremias Sulam

Are All Linear Regions Created Equal?

Matteo Gamba, Adrian Chmielewski-Anders, Josephine Sullivan, Hossein Azizpour, Mårten Björkman

Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression

Giacomo Meanti, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco

Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Chuanhao Li, Hongning Wang

Proximal Optimal Transport Modeling of Population Dynamics

Charlotte Bunne, Laetitia Papaxanthos, Andreas Krause, Marco Cuturi

Lifted Division for Lifted Hugin Belief Propagation

Moritz P. Hoffmann, Tanya Braun, Ralf Möller

QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning

Maxime Vono, Vincent Plassier, Alain Durmus, Aymeric Dieuleveut, Eric Moulines

Fast Fourier Transform Reductions for Bayesian Network Inference

Vincent Hsiao, Dana Nau, Rina Dechter

Iterative Alignment Flows

Zeyu Zhou, ZIYU GONG, Pradeep Ravikumar, David I. Inouye

A New Notion of Individually Fair Clustering: α-Equitable k-Center

Darshan Chakrabarti, John P. Dickerson, Seyed A. Esmaeili, Aravind Srinivasan, Leonidas Tsepenekas

Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits

Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Vidya K. Muthukumar, Ashwin Pananjady

Provable Lifelong Learning of Representations

Xinyuan Cao, Weiyang Liu, Santosh Vempala

Fair Disaster Containment via Graph-Cut Problems

Michael Dinitz, Aravind Srinivasan, Leonidas Tsepenekas, Anil Vullikanti

Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization

Yujia Wang, Lu Lin, Jinghui Chen

Differential privacy for symmetric log-concave mechanisms

Staal A. Vinterbo

Top K Ranking for Multi-Armed Bandit with Noisy Evaluations

Evrard Garcelon, Vashist Avadhanula, Alessandro Lazaric, Matteo Pirotta

Node Feature Kernels Increase Graph Convolutional Network Robustness

Mohamed El Amine Seddik, Changmin Wu, Johannes F. Lutzeyer, Michalis Vazirgiannis

Learning Competitive Equilibria in Exchange Economies with Bandit Feedback

Wenshuo Guo, Kirthevasan Kandasamy, Joseph Gonzalez, Michael Jordan, Ion Stoica

Conditional Linear Regression for Heterogeneous Covariances

Leda Liang, Brendan Juba

Transfer Learning with Gaussian Processes for Bayesian Optimization

Petru Tighineanu, Kathrin Skubch, Paul Baireuther, Attila Reiss, Felix Berkenkamp

Double Control Variates for Gradient Estimation in Discrete Latent Variable Models

Michalis Titsias, Jiaxin Shi

The Tree Loss: Improving Generalization with Many Classes

Yujie Wang, Mike Izbicki

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

Pratik Patil, Alessandro Rinaldo, Ryan Tibshirani

Orthogonal Multi-Manifold Enriching of Directed Networks

Ramit Sawhney, Shivam Agarwal, Atula T. Neerkaje, Kapil Jayesh Pathak

Learning Revenue-Maximizing Auctions With Differentiable Matching

Michael J. Curry, Uro Lyi, Tom Goldstein, John P. Dickerson

Performative Prediction in a Stateful World

Gavin Brown, Shlomi Hod, Iden Kalemaj

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

Jongha J. Ryu, Alankrita Bhatt, Young-Han Kim

Efficient Online Bayesian Inference for Neural Bandits

Gerardo Duran-Martin, Aleyna Kara, Kevin Murphy

Permutation Equivariant Layers for Higher Order Interactions

Horace Pan, Risi Kondor

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

James Brofos, Marylou Gabrie, Marcus A. Brubaker, Roy R. Lederman

Meta Learning MDPs with linear transition models

Robert Müller, Aldo Pacchiano

On Combining Bags to Better Learn from Label Proportions

Rishi Saket, Aravindan Raghuveer, Balaraman Ravindran

Learning in Stochastic Monotone Games with Decision-Dependent Data

Adhyyan Narang, Evan Faulkner, Dmitriy Drusvyatskiy, Maryam Fazel, Lillian Ratliff

Masked Training of Neural Networks with Partial Gradients

Amirkeivan Mohtashami, Martin Jaggi, Sebastian Stich

Harmless interpolation in regression and classification with structured features

Andrew D. Mcrae, Santhosh Karnik, Mark Davenport, Vidya K. Muthukumar

PAC Mode Estimation using PPR Martingale Confidence Sequences

Shubham Anand Jain, Rohan Shah, Sanit Gupta, Denil Mehta, Inderjeet J. Nair

Orbital MCMC

Kirill Neklyudov, Max Welling

A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learning

Alix LHERITIER, Nicolas Bondoux

Corruption-robust Offline Reinforcement Learning

Xuezhou Zhang, Yiding Chen, Xiaojin Zhu, Wen Sun

Acceleration in Distributed Optimization under Similarity

Ye Tian, Gesualdo Scutari, Tianyu Cao, Alexander Gasnikov

Efficient Kernelized UCB for Contextual Bandits

Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin

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

Romain Laroche, Remi Tachet des Combes

Fast and accurate optimization on the orthogonal manifold without retraction

Pierre Ablin, Gabriel Peyré

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

Yuqing Zhu, Yu-Xiang Wang

Estimators of Entropy and Information via Inference in Probabilistic Models

Feras Saad, Marco Cusumano-Towner, Vikash Mansinghka

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

Vibhor Porwal, Piyush Srivastava, Gaurav Sinha

SHAFF: Fast and consistent SHApley eFfect estimates via random Forests

Clement Benard, Gérard Biau, Sébastien Da Veiga, Erwan Scornet

Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge

Abhin Shah, Karthikeyan Shanmugam, Kartik Ahuja

TD-GEN: Graph Generation Using Tree Decomposition

Hamed Shirzad, Hossein Hajimirsadeghi, Amir H. Abdi, Greg Mori

Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity

Junchi Yang, Antonio Orvieto, Aurelien Lucchi, Niao He

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

Rickard K.A. Karlsson, Martin Willbo, Zeshan M. Hussain, Rahul G. Krishnan, David Sontag

Weak Separation in Mixture Models and Implications for Principal Stratification

nhật Hồ, Avi Feller, Evan Greif, Luke Miratrix, Natesh Pillai

New Coresets for Projective Clustering and Applications

Murad Tukan, Xuan Wu, Samson Zhou, Vladimir braverman, Dan Feldman

Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Animashree Anandkumar

Privacy Amplification by Decentralization

Edwige Cyffers, Aurélien Bellet

Wide Mean-Field Bayesian Neural Networks Ignore the Data

Beau Coker, Wessel P. Bruinsma, David R. Burt, Weiwei Pan, Finale Doshi-velez

How to scale hyperparameters for quickshift image segmentation

Damien Garreau

Crowdsourcing Regression: A Spectral Approach

Yaniv Tenzer, Omer Dror, Boaz Nadler, Erhan Bilal, Yuval Kluger

Particle-based Adversarial Local Distribution Regularization

Thanh Nguyen-Duc, Trung Le, He Zhao, Jianfei Cai, Dinh Phung

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

Alain Rakotomamonjy, Rémi Flamary, Joseph Salmon, Gilles Gasso

Modelling Non-Smooth Signals with Complex Spectral Structure

Wessel P. Bruinsma, Martin Tegnér, Richard E. Turner

Optimal transport with f-divergence regularization and generalized Sinkhorn algorithm

Dávid Terjék, Diego González-Sánchez

Margin-distancing for safe model explanation

Tom Yan, Chicheng Zhang

Kantorovich Mechanism for Pufferfish Privacy

Ni Ding

Predictive variational Bayesian inference as risk-seeking optimization

Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama

Off-Policy Risk Assessment for Markov Decision Processes

Audrey Huang, Liu Leqi, Zachary Lipton, Kamyar Azizzadenesheli

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

Thibault Sejourne, Francois-Xavier Vialard, Gabriel Peyré

Adversarially Robust Kernel Smoothing

Jia-Jie Zhu, Christina Kouridi, Yassine Nemmour, Bernhard Schölkopf

Variational Gaussian Processes: A Functional Analysis View

George Wynne, Veit Wild

Federated Myopic Community Detection with One-shot Communication

Chuyang Ke, Jean Honorio

Resampling Base Distributions of Normalizing Flows

Vincent Stimper, Bernhard Schölkopf, José Miguel Hernández-Lobato

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

Preetish Rath, Michael Hughes

Pulling back information geometry

Georgios Arvanitidis, Miguel González-Duque, Alison Pouplin, Dimitrios Kalatzis, Soren Hauberg

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

Jorge Silva, Felipe Tobar

Bayesian Link Prediction with Deep Graph Convolutional Gaussian Processes

Felix Opolka, Pietro Lió

Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets

Felix Opolka, Yin-Cong Zhi, Pietro Lió, Xiaowen Dong

Optimal Accounting of Differential Privacy via Characteristic Function

Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang

Lagrangian manifold Monte Carlo on Monge patches

Marcelo Hartmann, Mark Girolami, Arto Klami

Synthsonic: Fast, Probabilistic modeling and Synthesis of Tabular Data

Max Baak, Simon Brugman, Ilan Fridman Rojas, Lorraine Dalmeida, Ralph E.Q. Urlus

Improved Algorithms for Misspecified Linear Markov Decision Processes

Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R Srikant

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

Edward De Brouwer, Javier Gonzalez, Stephanie Hyland

Learning Proposals for Practical Energy-Based Regression

Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Schön

On Convergence of Lookahead in Smooth Games

Junsoo Ha, Gunhee Kim

A prior-based approximate latent Riemannian metric

Georgios Arvanitidis, Bogdan M. Georgiev, Bernhard Schölkopf

On the Consistency of Max-Margin Losses

Alex Nowak, Alessandro Rudi, Francis Bach

Variational Autoencoders: A Harmonic Perspective

Alexander Camuto, Matthew Willetts

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

Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi, Sohini Upadhyay, Himabindu Lakkaraju

Variational Continual Proxy-Anchor for Deep Metric Learning

Minyoung Kim, Ricardo Guerrero, Hai X. Pham, Vladimir Pavlovic

Safe Active Learning for Multi-Output Gaussian Processes

Cen-You Li, Barbara Rakitsch, Christoph Zimmer