AISTATS 2021

455 papers

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm

Majid Jahani, MohammadReza Nazari, Rachael Tappenden, Albert Berahas, Martin Takac

Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes

Manuel Haußmann, Sebastian Gerwinn, Andreas Look, Barbara Rakitsch, Melih Kandemir

On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions

Kai Brügge, Asja Fischer, Christian Igel

Low-Rank Generalized Linear Bandit Problems

Yangyi Lu, Amirhossein Meisami, Ambuj Tewari

Learning GPLVM with arbitrary kernels using the unscented transformation

Daniel de Souza, Diego Mesquita, João Paulo Gomes, César Lincoln Mattos

Approximating Lipschitz continuous functions with GroupSort neural networks

Ugo Tanielian, Gérard Biau

Curriculum Learning by Optimizing Learning Dynamics

Tianyi Zhou, Shengjie Wang, Jeff Bilmes

The Sample Complexity of Level Set Approximation

Francois Bachoc, Tommaso Cesari, Sébastien Gerchinovitz

A Stein Goodness-of-test for Exponential Random Graph Models

Wenkai Xu, Gesine Reinert

Active Learning with Maximum Margin Sparse Gaussian Processes

Weishi Shi, Qi Yu

Approximate Message Passing with Spectral Initialization for Generalized Linear Models

Marco Mondelli, Ramji Venkataramanan

Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures

Fanghui Liu, Xiaolin Huang, Yingyi Chen, Johan Suykens

On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems

Yingjie Bi, Javad Lavaei

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

Yingkai Li, Yining Wang, Xi Chen, Yuan Zhou

Deep Spectral Ranking

Ilkay Yildiz, Jennifer Dy, Deniz Erdogmus, Susan Ostmo, J. Peter Campbell

Fisher Auto-Encoders

Khalil Elkhalil, Ali Hasan, Jie Ding, Sina Farsiu, Vahid Tarokh

Benchmarking Simulation-Based Inference

Jan-Matthis Lueckmann, Jan Boelts, David Greenberg, Pedro Goncalves, Jakob Macke

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry

Tomohiro Hayase, Ryo Karakida

A Contraction Approach to Model-based Reinforcement Learning

Ting-Han Fan, Peter Ramadge

Online Sparse Reinforcement Learning

Botao Hao, Tor Lattimore, Csaba Szepesvári, Mengdi Wang

Online Active Model Selection for Pre-trained Classifiers

Mohammad Reza Karimi, Nezihe Merve Gürel, Bojan Karlaš, Johannes Rausch, Ce Zhang

Robust Imitation Learning from Noisy Demonstrations

Voot Tangkaratt, Nontawat Charoenphakdee, Masashi Sugiyama

A comparative study on sampling with replacement vs Poisson sampling in optimal subsampling

HaiYing Wang, Jiahui Zou

Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic Approximation

Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

Contextual Blocking Bandits

Soumya Basu, Orestis Papadigenopoulos, Constantine Caramanis, Sanjay Shakkottai

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification

Tianyi Lin, Zeyu Zheng, Elynn Chen, Marco Cuturi, Michael I. Jordan

Learning Smooth and Fair Representations

Xavier Gitiaux, Huzefa Rangwala

When MAML Can Adapt Fast and How to Assist When It Cannot

Sébastien Arnold, Shariq Iqbal, Fei Sha

Nonlinear Functional Output Regression: A Dictionary Approach

Dimitri Bouche, Marianne Clausel, François Roueff, Florence d’Alché-Buc

A Bayesian nonparametric approach to count-min sketch under power-law data streams

Emanuele Dolera, Stefano Favaro, Stefano Peluchetti

Online Forgetting Process for Linear Regression Models

Yuantong Li, Chi-Hua Wang, Guang Cheng

Alternating Direction Method of Multipliers for Quantization

Tianjian Huang, Prajwal Singhania, Maziar Sanjabi, Pabitra Mitra, Meisam Razaviyayn

Fully Gap-Dependent Bounds for Multinomial Logit Bandit

Jiaqi Yang

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

Xing Han, Sambarta Dasgupta, Joydeep Ghosh

Accelerating Metropolis-Hastings with Lightweight Inference Compilation

Feynman Liang, Nimar Arora, Nazanin Tehrani, Yucen Li, Michael Tingley

Fourier Bases for Solving Permutation Puzzles

Horace Pan, Risi Kondor

False Discovery Rates in Biological Networks

Lu Yu, Tobias Kaufmann, Johannes Lederer

Unconstrained MAP Inference, Exponentiated Determinantal Point Processes, and Exponential Inapproximability

Naoto Ohsaka

Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint

Yoichi Chikahara, Shinsaku Sakaue, Akinori Fujino, Hisashi Kashima

When OT meets MoM: Robust estimation of Wasserstein Distance

Guillaume Staerman, Pierre Laforgue, Pavlo Mozharovskyi, Florence d’Alché-Buc

Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns

Ziping Xu, Amirhossein Meisami, Ambuj Tewari

Regression Discontinuity Design under Self-selection

Sida Peng, Yang Ning

A Fast and Robust Method for Global Topological Functional Optimization

Yitzchak Solomon, Alexander Wagner, Paul Bendich

Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors

Nikhil Mehta, Kevin Liang, Vinay Kumar Verma, Lawrence Carin

On the proliferation of support vectors in high dimensions

Daniel Hsu, Vidya Muthukumar, Ji Xu

On Information Gain and Regret Bounds in Gaussian Process Bandits

Sattar Vakili, Kia Khezeli, Victor Picheny

Semi-Supervised Learning with Meta-Gradient

Taihong Xiao, Xin-Yu Zhang, Haolin Jia, Ming-Ming Cheng, Ming-Hsuan Yang

Regularized Policies are Reward Robust

Hisham Husain, Kamil Ciosek, Ryota Tomioka

CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices

Valerii Likhosherstov, Jared Davis, Krzysztof Choromanski, Adrian Weller

One-Round Communication Efficient Distributed M-Estimation

Yajie Bao, Weijia Xiong

Graphical Normalizing Flows

Antoine Wehenkel, Gilles Louppe

Differentiable Greedy Algorithm for Monotone Submodular Maximization: Guarantees, Gradient Estimators, and Applications

Shinsaku Sakaue

Projection-Free Optimization on Uniformly Convex Sets

Thomas Kerdreux, Alexandre d’Aspremont, Sebastian Pokutta

LassoNet: Neural Networks with Feature Sparsity

Ismael Lemhadri, Feng Ruan, Rob Tibshirani

On the Effect of Auxiliary Tasks on Representation Dynamics

Clare Lyle, Mark Rowland, Georg Ostrovski, Will Dabney