AISTATS 2021

455 papers

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtarik, Sebastian Stich

A unified view of likelihood ratio and reparameterization gradients

Paavo Parmas, Masashi Sugiyama

Does Invariant Risk Minimization Capture Invariance?

Pritish Kamath, Akilesh Tangella, Danica Sutherland, Nathan Srebro

Graph Gamma Process Linear Dynamical Systems

Rahi Kalantari, Mingyuan Zhou

Improving Classifier Confidence using Lossy Label-Invariant Transformations

Sooyong Jang, Insup Lee, James Weimer

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Sebastian Stich, Amirkeivan Mohtashami, Martin Jaggi

Hidden Cost of Randomized Smoothing

Jeet Mohapatra, Ching-Yun Ko, Lily Weng, Pin-Yu Chen, Sijia Liu

Meta-Learning Divergences for Variational Inference

Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp

Regularized ERM on random subspaces

Andrea Della Vecchia, Jaouad Mourtada, Ernesto De Vito, Lorenzo Rosasco

Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries

Steve Hanneke, Liu Yang

Improved Exploration in Factored Average-Reward MDPs

Mohammad Sadegh Talebi, Anders Jonsson, Odalric Maillard

Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization

Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith

Bayesian Active Learning by Soft Mean Objective Cost of Uncertainty

Guang Zhao, Edward Dougherty, Byung-Jun Yoon, Francis J. Alexander, Xiaoning Qian

Faster & More Reliable Tuning of Neural Networks: Bayesian Optimization with Importance Sampling

Setareh Ariafar, Zelda Mariet, Dana Brooks, Jennifer Dy, Jasper Snoek

Learning Shared Subgraphs in Ising Model Pairs

Burak Varici, Saurabh Sihag, Ali Tajer

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Hossein Shokri Ghadikolaei, Sebastian Stich, Martin Jaggi

Flow-based Alignment Approaches for Probability Measures in Different Spaces

Tam Le, nhật Hồ, Makoto Yamada

On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent Variable Models

Yuyang Shi, Rob Cornish

Model updating after interventions paradoxically introduces bias

James Liley, Samuel Emerson, Bilal Mateen, Catalina Vallejos, Louis Aslett

An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte Carlo

Matthew Hoffman, Alexey Radul, Pavel Sountsov

Longitudinal Variational Autoencoder

Siddharth Ramchandran, Gleb Tikhonov, Kalle Kujanpää, Miika Koskinen, Harri Lahdesmaki

Asymptotics of Ridge(less) Regression under General Source Condition

Dominic Richards, Jaouad Mourtada, Lorenzo Rosasco

Rate-Regularization and Generalization in Variational Autoencoders

Alican Bozkurt, Babak Esmaeili, Jean-Baptiste Tristan, Dana Brooks, Jennifer Dy

Differentiating the Value Function by using Convex Duality

Sheheryar Mehmood, Peter Ochs

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Konstantinos Panousis, Sotirios Chatzis, Antonios Alexos, Sergios Theodoridis

Differentiable Divergences Between Time Series

Mathieu Blondel, Arthur Mensch, Jean-philippe Vert

Combinatorial Gaussian Process Bandits with Probabilistically Triggered Arms

Ilker Demirel, Cem Tekin

Entropy Partial Transport with Tree Metrics: Theory and Practice

Tam Le, Truyen Nguyen

Convergence Properties of Stochastic Hypergradients

Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo

Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models

Leena C. Vankadara, Sebastian Bordt, Ulrike Von Luxburg, Debarghya Ghoshdastidar

Robust Learning under Strong Noise via SQs

Ioannis Anagnostides, Themis Gouleakis, Ali Marashian

On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity

Yuuki Takai, Akiyoshi Sannai, Matthieu Cordonnier

Learning Temporal Point Processes with Intermittent Observations

Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, Abir De

Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry

Qadeer Khan, Patrick Wenzel, Daniel Cremers

Direct-Search for a Class of Stochastic Min-Max Problems

Sotirios-Konstantinos Anagnostidis, Aurelien Lucchi, Youssef Diouane

Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions

Yihan Wu, Aleksandar Bojchevski, Aleksei Kuvshinov, Stephan Günnemann

Distribution Regression for Sequential Data

Maud Lemercier, Cristopher Salvi, Theodoros Damoulas, Edwin Bonilla, Terry Lyons

A Scalable Gradient Free Method for Bayesian Experimental Design with Implicit Models

Jiaxin Zhang, Sirui Bi, Guannan Zhang

Minimax Estimation of Laplacian Constrained Precision Matrices

Jiaxi Ying, Jose Vinicius de Miranda Cardoso, Daniel Palomar

Deep Generative Missingness Pattern-Set Mixture Models

Sahra Ghalebikesabi, Rob Cornish, Chris Holmes, Luke Kelly

Latent Gaussian process with composite likelihoods and numerical quadrature

Siddharth Ramchandran, Miika Koskinen, Harri Lahdesmaki

GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences

Mucong Ding, Constantinos Daskalakis, Soheil Feizi

Causal Inference under Networked Interference and Intervention Policy Enhancement

Yunpu Ma, Volker Tresp

Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits

Marc Abeille, Louis Faury, Clément Calauzènes

On the Memory Mechanism of Tensor-Power Recurrent Models

Hejia Qiu, CHAO LI, Ying Weng, Zhun Sun, Xingyu He

One-pass Stochastic Gradient Descent in overparametrized two-layer neural networks

Hanjing Zhu, Jiaming Xu

Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain

Takahiro Mimori, Keiko Sasada, Hirotaka Matsui, Issei Sato

Learning Bijective Feature Maps for Linear ICA

Alexander Camuto, Matthew Willetts, Chris Holmes, Brooks Paige, Stephen Roberts

Couplings for Multinomial Hamiltonian Monte Carlo

Kai Xu, Tor Erlend Fjelde, Charles Sutton, Hong Ge

Dirichlet Pruning for Convolutional Neural Networks

Kamil Adamczewski, Mijung Park

Sequential Random Sampling Revisited: Hidden Shuffle Method

Michael Shekelyan, Graham Cormode

Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model

Nafiseh Ghoroghchian, Gautam Dasarathy, Stark Draper

Logistic Q-Learning

Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu

A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models

Samet Oymak, Talha Cihad Gulcu

Revisiting Projection-free Online Learning: the Strongly Convex Case

Ben Kretzu, Dan Garber

The Base Measure Problem and its Solution

Alexey Radul, Boris Alexeev

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization

Vikas Garg, Adam Tauman Kalai, Katrina Ligett, Steven Wu

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders

Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom Rainforth

Local SGD: Unified Theory and New Efficient Methods

Eduard Gorbunov, Filip Hanzely, Peter Richtarik

Spectral Tensor Train Parameterization of Deep Learning Layers

Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis

A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Emilie Kaufmann, Michal Valko

Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models

Jan Achterhold, Joerg Stueckler

Causal Autoregressive Flows

Ilyes Khemakhem, Ricardo Monti, Robert Leech, Aapo Hyvärinen

Scalable Gaussian Process Variational Autoencoders

Metod Jazbec, Matt Ashman, Vincent Fortuin, Michael Pearce, Stephan Mandt

Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-Information

Prathamesh Mayekar, Ananda Theertha Suresh, Himanshu Tyagi

An Analysis of LIME for Text Data

Dina Mardaoui, Damien Garreau

Probabilistic Sequential Matrix Factorization

Omer Deniz Akyildiz, Gerrit van den Burg, Theodoros Damoulas, Mark Steel

Online Robust Control of Nonlinear Systems with Large Uncertainty

Dimitar Ho, Hoang Le, John Doyle, Yisong Yue

Calibrated Adaptive Probabilistic ODE Solvers

Nathanael Bosch, Philipp Hennig, Filip Tronarp

Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression

Ian Covert, Su-in Lee

Rao-Blackwellised parallel MCMC

Tobias Schwedes, Ben Calderhead

Hyperbolic graph embedding with enhanced semi-implicit variational inference.

Ali Lotfi Rezaabad, Rahi Kalantari, Sriram Vishwanath, Mingyuan Zhou, Jonathan Tamir

Offline detection of change-points in the mean for stationary graph signals.

Alejandro de la Concha Duarte, Nicolas Vayatis, Argyris Kalogeratos

Tracking Regret Bounds for Online Submodular Optimization

Tatsuya Matsuoka, Shinji Ito, Naoto Ohsaka

Active Learning under Label Shift

Eric Zhao, Anqi Liu, Animashree Anandkumar, Yisong Yue

Towards Flexible Device Participation in Federated Learning

Yichen Ruan, Xiaoxi Zhang, Shu-Che Liang, Carlee Joe-Wong

A Spectral Analysis of Dot-product Kernels

meyer scetbon, Zaïd Harchaoui

No-Regret Reinforcement Learning with Heavy-Tailed Rewards

Vincent Zhuang, Yanan Sui

Good Classifiers are Abundant in the Interpolating Regime

Ryan Theisen, Jason Klusowski, Michael Mahoney

A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits

Kei Takemura, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Antti Koskela, Joonas Jälkö, Lukas Prediger, Antti Honkela

Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC

Priyank Jaini, Didrik Nielsen, Max Welling

Online Model Selection for Reinforcement Learning with Function Approximation

Jonathan Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill

Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning

Zhengqing Zhou, Zhengyuan Zhou, Qinxun Bai, Linhai Qiu, Jose Blanchet

Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences

Sreejith Sreekumar, Zhengxin Zhang, Ziv Goldfeld

Understanding Robustness in Teacher-Student Setting: A New Perspective

Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li

Provably Efficient Safe Exploration via Primal-Dual Policy Optimization

Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo Jovanovic

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

Frederik Kunstner, Raunak Kumar, Mark Schmidt

Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation

Mayee Chen, Benjamin Cohen-Wang, Stephen Mussmann, Frederic Sala, Christopher Re

Efficient Designs Of SLOPE Penalty Sequences In Finite Dimension

Yiliang Zhang, Zhiqi Bu

Taming heavy-tailed features by shrinkage

Ziwei Zhu, Wenjing Zhou

Fair for All: Best-effort Fairness Guarantees for Classification

Anilesh Krishnaswamy, Zhihao Jiang, Kangning Wang, Yu Cheng, Kamesh Munagala

Automatic Differentiation Variational Inference with Mixtures

Warren Morningstar, Sharad Vikram, Cusuh Ham, Andrew Gallagher, Joshua Dillon

Product Manifold Learning

Sharon Zhang, Amit Moscovich, Amit Singer

Density of States Estimation for Out of Distribution Detection

Warren Morningstar, Cusuh Ham, Andrew Gallagher, Balaji Lakshminarayanan, Alex Alemi

Prediction with Finitely many Errors Almost Surely

Changlong Wu, Narayana Santhanam

A Hybrid Approximation to the Marginal Likelihood

Eric Chuu, Debdeep Pati, Anirban Bhattacharya

Principal Subspace Estimation Under Information Diffusion

Fan Zhou, Ping Li, Zhixin Zhou

Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees

Alessio Mazzetto, Dylan Sam, Andrew Park, Eli Upfal, Stephen Bach