AISTATS 2021

455 papers

A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks

Zhiqi Bu, Shiyun Xu, Kan Chen

Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge Regression

Pratik Patil, Yuting Wei, Alessandro Rinaldo, Ryan Tibshirani

Sketch based Memory for Neural Networks

Rina Panigrahy, Xin Wang, Manzil Zaheer

TenIPS: Inverse Propensity Sampling for Tensor Completion

Chengrun Yang, Lijun Ding, Ziyang Wu, Madeleine Udell

Contrastive learning of strong-mixing continuous-time stochastic processes

Bingbin Liu, Pradeep Ravikumar, Andrej Risteski

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

Huichen Li, Linyi Li, Xiaojun Xu, Xiaolu Zhang, Shuang Yang

Kernel Interpolation for Scalable Online Gaussian Processes

Samuel Stanton, Wesley Maddox, Ian Delbridge, Andrew Gordon Wilson

Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon

Jeremiah Liu

Associative Convolutional Layers

Hamed Omidvar, Vahideh Akhlaghi, Hao Su, Massimo Franceschetti, Rajesh Gupta

Dynamic Cutset Networks

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

DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks

Shiyun Xu, Zhiqi Bu

Experimental Design for Regret Minimization in Linear Bandits

Andrew Wagenmaker, Julian Katz-Samuels, Kevin Jamieson

Tensor Networks for Probabilistic Sequence Modeling

Jacob Miller, Guillaume Rabusseau, John Terilla

Efficient Balanced Treatment Assignments for Experimentation

David Arbour, Drew Dimmery, Anup Rao

Fast and Smooth Interpolation on Wasserstein Space

Sinho Chewi, Julien Clancy, Thibaut Le Gouic, Philippe Rigollet, George Stepaniants

Meta Learning in the Continuous Time Limit

Ruitu Xu, Lin Chen, Amin Karbasi

Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances

Hunter Lang, Aravind Reddy, David Sontag, Aravindan Vijayaraghavan

The Multiple Instance Learning Gaussian Process Probit Model

Fulton Wang, Ali Pinar

Causal Modeling with Stochastic Confounders

Thanh Vinh Vo, Pengfei Wei, Wicher Bergsma, Tze Yun Leong

Multi-Armed Bandits with Cost Subsidy

Deeksha Sinha, Karthik Abinav Sankararaman, Abbas Kazerouni, Vashist Avadhanula

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

Chen-Yu Wei, Mehdi Jafarnia Jahromi, Haipeng Luo, Rahul Jain

Training a Single Bandit Arm

Eren Ozbay, Vijay Kamble

Detection and Defense of Topological Adversarial Attacks on Graphs

Yingxue Zhang, Florence Regol, Soumyasundar Pal, Sakif Khan, Liheng Ma

SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups

Hyun-Suk Lee, Cong Shen, William Zame, Jang-Won Lee, Mihaela van der Schaar

Faster Kernel Interpolation for Gaussian Processes

Mohit Yadav, Daniel Sheldon, Cameron Musco

Robust hypothesis testing and distribution estimation in Hellinger distance

Ananda Theertha Suresh

Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge Regression

Yifan Chen, Yun Yang

Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and Algorithms

Tianyu Ding, Zhihui Zhu, Manolis Tsakiris, René Vidal, Daniel Robinson

Fast Statistical Leverage Score Approximation in Kernel Ridge Regression

Yifan Chen, Yun Yang

Hierarchical Inducing Point Gaussian Process for Inter-domian Observations

Luhuan Wu, Andrew Miller, Lauren Anderson, Geoff Pleiss, David Blei

Federated Multi-armed Bandits with Personalization

Chengshuai Shi, Cong Shen, Jing Yang

Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints

Omid Sadeghi, Maryam Fazel

An Optimal Reduction of TV-Denoising to Adaptive Online Learning

Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang

Large Scale K-Median Clustering for Stable Clustering Instances

Konstantin Voevodski

Location Trace Privacy Under Conditional Priors

Casey Meehan, Kamalika Chaudhuri

Follow Your Star: New Frameworks for Online Stochastic Matching with Known and Unknown Patience

Brian Brubach, Nathaniel Grammel, Will Ma, Aravind Srinivasan

Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning

Yunhao Tang, Alp Kucukelbir

DAG-Structured Clustering by Nearest Neighbors

Nicholas Monath, Manzil Zaheer, Kumar Avinava Dubey, Amr Ahmed, Andrew McCallum

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou

Significance of Gradient Information in Bayesian Optimization

Shubhanshu Shekhar, Tara Javidi

Stochastic Bandits with Linear Constraints

Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett, Heinrich Jiang

Power of Hints for Online Learning with Movement Costs

Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit

Mirror Descent View for Neural Network Quantization

Thalaiyasingam Ajanthan, Kartik Gupta, Philip Torr, Richad Hartley, Puneet Dokania

Animal pose estimation from video data with a hierarchical von Mises-Fisher-Gaussian model

Libby Zhang, Tim Dunn, Jesse Marshall, Bence Olveczky, Scott Linderman

Causal Inference with Selectively Deconfounded Data

Kyra Gan, Andrew Li, Zachary Lipton, Sridhar Tayur

Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective

Jacky Zhang, Rajiv Khanna, Anastasios Kyrillidis, Sanmi Koyejo

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions

Hossein Taheri, Ramtin Pedarsani, CHRISTOS THRAMPOULIDIS

Provably Eﬃcient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case

Yufeng Zhang, Zhuoran Yang, Zhaoran Wang

A Change of Variables Method For Rectangular Matrix-Vector Products

Edmond Cunningham, Madalina Fiterau

Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization

Jelena Diakonikolas, Constantinos Daskalakis, Michael I. Jordan

Fast Adaptation with Linearized Neural Networks

Wesley Maddox, Shuai Tang, Pablo Moreno, Andrew Gordon Wilson, Andreas Damianou

Approximation Algorithms for Orthogonal Non-negative Matrix Factorization

Moses Charikar, Lunjia Hu

Variational inference for nonlinear ordinary differential equations

Sanmitra Ghosh, Paul Birrell, Daniela De Angelis

Influence Decompositions For Neural Network Attribution

Kyle Reing, Greg Ver Steeg, Aram Galstyan

Random Coordinate Underdamped Langevin Monte Carlo

ZHIYAN DING, Qin Li, Jianfeng Lu, Stephen Wright

Sample Elicitation

Jiaheng Wei, Zuyue Fu, Yang Liu, Xingyu Li, Zhuoran Yang

Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration

Shengjia Zhao, Stefano Ermon

Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Principal Component Regression with Semirandom Observations via Matrix Completion

Aditya Bhaskara, Aravinda Kanchana Ruwanpathirana, Maheshakya Wijewardena

Reinforcement Learning for Constrained Markov Decision Processes

Ather Gattami, Qinbo Bai, Vaneet Aggarwal

One-Sketch-for-All: Non-linear Random Features from Compressed Linear Measurements

Xiaoyun Li, Ping Li

Evading the Curse of Dimensionality in Unconstrained Private GLMs

Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta

Regret-Optimal Filtering

Oron Sabag, Babak Hassibi

Continuum-Armed Bandits: A Function Space Perspective

Shashank Singh

Evaluating Model Robustness and Stability to Dataset Shift

Adarsh Subbaswamy, Roy Adams, Suchi Saria

Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs

Alden Green, Sivaraman Balakrishnan, Ryan Tibshirani

Matérn Gaussian Processes on Graphs

Viacheslav Borovitskiy, Iskander Azangulov, Alexander Terenin, Peter Mostowsky, Marc Deisenroth

Linear Models are Robust Optimal Under Strategic Behavior

Wei Tang, Chien-Ju Ho, Yang Liu

Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning

Zachary Charles, Jakub Konečný

Direct Loss Minimization for Sparse Gaussian Processes

Yadi Wei, Rishit Sheth, Roni Khardon

Private optimization without constraint violations

Andres Munoz, Umar Syed, Sergei Vassilvtiskii, Ellen Vitercik

A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets

Gauthier Gidel, David Balduzzi, Wojciech Czarnecki, Marta Garnelo, Yoram Bachrach

Designing Transportable Experiments Under S-admissability

My Phan, David Arbour, Drew Dimmery, Anup Rao

CLAR: Contrastive Learning of Auditory Representations

Haider Al-Tahan, Yalda Mohsenzadeh

Shuffled Model of Differential Privacy in Federated Learning

Antonious Girgis, Deepesh Data, Suhas Diggavi, Peter Kairouz, Ananda Theertha Suresh

A Statistical Perspective on Coreset Density Estimation

Paxton Turner, Jingbo Liu, Philippe Rigollet

Efficient Interpolation of Density Estimators

Paxton Turner, Jingbo Liu, Philippe Rigollet

Non-Stationary Off-Policy Optimization

Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed

On the Consistency of Metric and Non-Metric K-Medoids

He Jiang, Ery Arias-Castro

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?

Chaoqi Wang, Shengyang Sun, Roger Grosse

Cluster Trellis: Data Structures & Algorithms for Exact Inference in Hierarchical Clustering

Sebastian Macaluso, Craig Greenberg, Nicholas Monath, Ji Ah Lee, Patrick Flaherty

Reinforcement Learning for Mean Field Games with Strategic Complementarities

Kiyeob Lee, Desik Rengarajan, Dileep Kalathil, Srinivas Shakkottai

Statistical Guarantees for Transformation Based Models with applications to Implicit Variational Inference

Sean Plummer, Shuang Zhou, Anirban Bhattacharya, David Dunson, Debdeep Pati

Hierarchical Clustering in General Metric Spaces using Approximate Nearest Neighbors

Benjamin Moseley, Sergei Vassilvtiskii, Yuyan Wang

Bayesian Inference with Certifiable Adversarial Robustness

Matthew Wicker, Luca Laurenti, Andrea Patane, Zhuotong Chen, Zheng Zhang

Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples

Yixing Zhang, Xiuyuan Cheng, Galen Reeves

Learning the Truth From Only One Side of the Story

Heinrich Jiang, Qijia Jiang, Aldo Pacchiano

Differentially Private Weighted Sampling

Edith Cohen, Ofir Geri, Tamas Sarlos, Uri Stemmer

Minimal enumeration of all possible total effects in a Markov equivalence class

Richard Guo, Emilija Perkovic

On the Linear Convergence of Policy Gradient Methods for Finite MDPs

Jalaj Bhandari, Daniel Russo

Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data

Yu Gong, Hossein Hajimirsadeghi, Jiawei He, Thibaut Durand, Greg Mori

RankDistil: Knowledge Distillation for Ranking

Sashank Reddi, Rama Kumar Pasumarthi, Aditya Menon, Ankit Singh Rawat, Felix Yu

Variational Autoencoder with Learned Latent Structure

Marissa Connor, Gregory Canal, Christopher Rozell

Federated Learning with Compression: Unified Analysis and Sharp Guarantees

Farzin Haddadpour, Mohammad Mahdi Kamani, Aryan Mokhtari, Mehrdad Mahdavi

Group testing for connected communities

Pavlos Nikolopoulos, Sundara Rajan Srinivasavaradhan, Tao GUO, Christina Fragouli, Suhas Diggavi

A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh, Ke Wu

The Sample Complexity of Meta Sparse Regression

Zhanyu Wang, Jean Honorio

Differentiable Causal Discovery Under Unmeasured Confounding

Rohit Bhattacharya, Tushar Nagarajan, Daniel Malinsky, Ilya Shpitser

Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent

Suriya Gunasekar, Blake Woodworth, Nathan Srebro

Optimal query complexity for private sequential learning against eavesdropping

Jiaming Xu, Kuang Xu, Dana Yang