AISTATS 2022

492 papers

Recoverability Landscape of Tree Structured Markov Random Fields under Symmetric Noise

Ashish Katiyar, Soumya Basu, Vatsal Shah, Constantine Caramanis

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

Robin A. Brown, Edward Schmerling, Navid Azizan, Marco Pavone

Fast Sparse Classification for Generalized Linear and Additive Models

Jiachang Liu, Chudi Zhong, Margo Seltzer, Cynthia Rudin

Calibration Error for Heterogeneous Treatment Effects

Yizhe Xu, Steve Yadlowsky

Asynchronous Distributed Optimization with Stochastic Delays

Margalit R. Glasgow, Mary Wootters

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

Yubo Zhuang, Xiaohui Chen, Yun Yang

On Learning Mixture Models with Sparse Parameters

Soumyabrata Pal, Arya Mazumdar

Second-Order Sensitivity Analysis for Bilevel Optimization

Robert Dyro, Edward Schmerling, Nikos Arechiga, Marco Pavone

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

Jiaojiao Fan, Isabel Haasler, Johan Karlsson, Yongxin Chen

Best Arm Identification with Safety Constraints

Zhenlin Wang, Andrew J. Wagenmaker, Kevin Jamieson

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

Yizhou Chen, Shizhuo Zhang, Bryan Kian Hsiang Low

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

Margalit R. Glasgow, Honglin Yuan, Tengyu Ma

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

Daniel Csillag, Carolina Piazza, Thiago Ramos, João Vitor Romano, Roberto I. Oliveira

Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

Yeshu Li, Zhan Shi, Xinhua Zhang, Brian Ziebart

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

Chirag Agarwal, Marinka Zitnik, Himabindu Lakkaraju

Regret, stability & fairness in matching markets with bandit learners

Sarah H. Cen, Devavrat Shah

Nonparametric Relational Models with Superrectangulation

Masahiro Nakano, Ryo Nishikimi, Yasuhiro Fujiwara, Akisato Kimura, Takeshi Yamada

Structured Multi-task Learning for Molecular Property Prediction

Shengchao Liu, Meng Qu, Zuobai Zhang, Huiyu Cai, Jian Tang

Structured variational inference in Bayesian state-space models

Honggang Wang, Anirban Bhattacharya, Debdeep Pati, Yun Yang

Online Continual Adaptation with Active Self-Training

Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang

Variance Minimization in the Wasserstein Space for Invariant Causal Prediction

Guillaume G. Martinet, Alexander Strzalkowski, Barbara Engelhardt

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

Yongchan Kwon, James Zou

Improved Approximation Algorithms for Individually Fair Clustering

Ali Vakilian, Mustafa Yalciner

Optimal estimation of Gaussian DAG models

Ming Gao, Wai Ming Tai, Bryon Aragam

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization

Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

Decoupling Local and Global Representations of Time Series

Sana Tonekaboni, Chun-Liang Li, Sercan Ö. Arik, Anna Goldenberg, Tomas Pfister

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

Yuheng Bu, Gholamali Aminian, Laura Toni, Gregory W. Wornell, Miguel Rodrigues

Fundamental limits for rank-one matrix estimation with groupwise heteroskedasticity

Joshua K. Behne, Galen Reeves

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

Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg

Contrasting the landscape of contrastive and non-contrastive learning

Ashwini Pokle, Jinjin Tian, Yuchen Li, Andrej Risteski

Reconstructing Test Labels from Noisy Loss Functions

Abhinav Aggarwal, Shiva Kasiviswanathan, Zekun Xu, Oluwaseyi Feyisetan, Nathanael Teissier

Convergence of online k-means

Geelon So, Gaurav Mahajan, Sanjoy Dasgupta

Debiasing Samples from Online Learning Using Bootstrap

Ningyuan Chen, Xuefeng GAO, Yi Xiong

Look-Ahead Acquisition Functions for Bernoulli Level Set Estimation

Benjamin Letham, Phillip Guan, Chase Tymms, Eytan Bakshy, Michael Shvartsman

Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory

Zhiyu Zhang, Ashok Cutkosky, Ioannis Paschalidis

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

Gideon Dresdner, Maria-Luiza Vladarean, Gunnar Rätsch, Francesco Locatello, Volkan Cevher

The Curse of Passive Data Collection in Batch Reinforcement Learning

Chenjun Xiao, Ilbin Lee, Bo Dai, Dale Schuurmans, Csaba Szepesvári

Amortized Rejection Sampling in Universal Probabilistic Programming

Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Gunes Baydin

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

Zai Shi, Atilla Eryilmaz

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

Shuai Xiao, Zaifan Jiang, Shuang Yang

Online Control of the False Discovery Rate under "Decision Deadlines"

Aaron J. Fisher

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

Devansh Bisla, Jing Wang, Anna Choromanska

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

Warren R. Morningstar, Alex Alemi, Joshua V. Dillon

Relational Neural Markov Random Fields

Yuqiao Chen, Sriraam Natarajan, Nicholas Ruozzi

Firebolt: Weak Supervision Under Weaker Assumptions

Zhaobin Kuang, Chidubem G. Arachie, Bangyong Liang, Pradyumna Narayana, Giulia DeSalvo

Hardness of Learning a Single Neuron with Adversarial Label Noise

Ilias Diakonikolas, Daniel Kane, Pasin Manurangsi, Lisheng Ren

On the Convergence of Continuous Constrained Optimization for Structure Learning

Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke, Simon Lacoste-Julien, Kun Zhang

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

Murat A. Erdogdu, Rasa Hosseinzadeh, Shunshi Zhang

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

Youngsuk Park, Danielle Maddix, Francois-Xavier Aubet, Kelvin Kan, Jan Gasthaus

Nuances in Margin Conditions Determine Gains in Active Learning

Samory Kpotufe, Gan Yuan, Yunfan Zhao

Towards Federated Bayesian Network Structure Learning with Continuous Optimization

Ignavier Ng, Kun Zhang

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

Alex R. Dytso, Mario Goldenbaum, H. Vincent Poor, Shlomo Shamai

Mode estimation on matrix manifolds: Convergence and robustness

Hiroaki Sasaki, Jun-ichiro Hirayama, Takafumi Kanamori

Two-Sample Test with Kernel Projected Wasserstein Distance

Jie Wang, RUI GAO, Yao Xie

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

Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu

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

Hugh Dance, Brooks Paige

Vanishing Curvature in Randomly Initialized Deep ReLU Networks

Antonio Orvieto, Jonas Köhler, Dario Pavllo, Thomas Hofmann, Aurelien Lucchi

Optimal channel selection with discrete QCQP

Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

Deep Non-crossing Quantiles through the Partial Derivative

Axel Brando, Barcelona Supercomputing Center, )*; and Joan Gimeno, Jose Rodriguez-Serrano, Jordi Vitria

Stochastic Extragradient: General Analysis and Improved Rates

Eduard Gorbunov, Hugo Berard, Gauthier Gidel, Nicolas Loizou

Generalised GPLVM with Stochastic Variational Inference

Vidhi Lalchand, Aditya Ravuri, Neil D. Lawrence

Federated Functional Gradient Boosting

Zebang Shen, Hamed Hassani, Satyen Kale, Amin Karbasi

Tuning-Free Generalized Hamiltonian Monte Carlo

Matthew D. Hoffman, Pavel Sountsov

Asymptotically Optimal Locally Private Heavy Hitters via Parameterized Sketches

Hao Wu, Anthony Wirth

Complex Momentum for Optimization in Games

Jonathan P. Lorraine, David Acuna, Paul Vicol, David Duvenaud

Hierarchical Bayesian Bandits

Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh

Optimal Compression of Locally Differentially Private Mechanisms

Abhin Shah, Wei-Ning Chen, Johannes Ballé, Peter Kairouz, Lucas Theis

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

Guodong Zhang, Yuanhao Wang, Laurent Lessard, Roger B. Grosse

Nearly Optimal Algorithms for Level Set Estimation

Blake Mason, Lalit Jain, Subhojyoti Mukherjee, Romain Camilleri, Kevin Jamieson

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal

Thompson Sampling with a Mixture Prior

Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh, Craig Boutilier

Dropout as a Regularizer of Interaction Effects

Benjamin J. Lengerich, Eric Xing, Rich Caruana

Efficient interventional distribution learning in the PAC framework

Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, Vedant Raval, Vinodchandran N. Variyam

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

Sumedh A. Sontakke, Stephen Iota, Zizhao Hu, Arash Mehrjou, Laurent Itti

On perfectness in Gaussian graphical models

Arash Amini, Bryon Aragam, Qing Zhou

Approximate Top-m Arm Identification with Heterogeneous Reward Variances

Ruida Zhou, Chao Tian

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

Eli N. Weinstein, Alan N. Amin, Will S. Grathwohl, Daniel Kassler, Jean Disset

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

Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni, Miguel Rodrigues

Chernoff Sampling for Active Testing and Extension to Active Regression

Subhojyoti Mukherjee, Ardhendu S. Tripathy, Robert Nowak

Adaptive Multi-Goal Exploration

Jean Tarbouriech, Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Michal Valko

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

Marco Rando, Luigi Carratino, Silvia Villa, Lorenzo Rosasco

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

Sebastian Bordt, Ulrike Von Luxburg

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

Yingyi Ma, Xinhua Zhang

Cycle Consistent Probability Divergences Across Different Spaces

Zhengxin Zhang, Youssef Mroueh, Ziv Goldfeld, Bharath Sriperumbudur

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

Dominic Danks, Christopher Yau

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

AmirEmad Ghassami, Andrew Ying, Ilya Shpitser, Eric Tchetgen Tchetgen

Investigating the Role of Negatives in Contrastive Representation Learning

Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra

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

Anant Raj, Pooria Joulani, András György, Csaba Szepesvári

On the Assumptions of Synthetic Control Methods

Claudia Shi, Dhanya Sridhar, Vishal Misra, David Blei

Multi-class classification in nonparametric active learning

Boris Ndjia Njike, Xavier Siebert

Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks

QIN DING, Cho-jui Hsieh, James Sharpnack

Neural score matching for high-dimensional causal inference

Oscar Clivio, Fabian Falck, Brieuc Lehmann, George Deligiannidis, Chris Holmes

Label differential privacy via clustering

Hossein Esfandiari, Vahab Mirrokni, Umar Syed, Sergei Vassilvitskii

Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes

Elvis Nava, Mojmir Mutny, Andreas Krause

On the equivalence of Oja’s algorithm and GROUSE

Laura Balzano

A Predictive Approach to Bayesian Nonparametric Survival Analysis

Edwin Fong, Brieuc Lehmann

Sensing Cox Processes via Posterior Sampling and Positive Bases

Mojmir Mutny, Andreas Krause

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

Hsu Kao, Vijay Subramanian

Conditionally Tractable Density Estimation using Neural Networks

Hailiang Dong, Chiradeep Roy, Tahrima Rahman, Vibhav Gogate, Nicholas Ruozzi

Weighted Gaussian Process Bandits for Non-stationary Environments

Yuntian Deng, Xingyu Zhou, Baekjin Kim, Ambuj Tewari, Abhishek Gupta