AISTATS 2020

423 papers

How fine can fine-tuning be? Learning efficient language models

Evani Radiya-Dixit, Xin Wang

Approximate Cross-Validation in High Dimensions with Guarantees

William Stephenson, Tamara Broderick

Balanced Off-Policy Evaluation in General Action Spaces

Arjun Sondhi, David Arbour, Drew Dimmery

Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models

Benjamin Lengerich, Sarah Tan, Chun-Hao Chang, Giles Hooker, Rich Caruana

Stochastic Linear Contextual Bandits with Diverse Contexts

Weiqiang Wu, Jing Yang, Cong Shen

Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks

Jinming Xu, Ye Tian, Ying Sun, Gesualdo Scutari

Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness

Antônio H. Ribeiro, Koen Tiels, Luis A. Aguirre, Thomas Schön

Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions

Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Marcello Restelli

Decentralized gradient methods: does topology matter?

Giovanni Neglia, CHUAN XU, Don Towsley, Gianmarco Calbi

Calibrated Surrogate Maximization of Linear-fractional Utility in Binary Classification

Han Bao, Masashi Sugiyama

Fairness Evaluation in Presence of Biased Noisy Labels

Riccardo Fogliato, Alexandra Chouldechova, Max G’Sell

Dynamic content based ranking

Seppo Virtanen, Mark Girolami

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning

Yao Zhang, Daniel Jarrett, Mihaela Schaar

Derivative-Free & Order-Robust Optimisation

Haitham Ammar, Victor Gabillon, Rasul Tutunov, Michal Valko

Domain-Liftability of Relational Marginal Polytopes

Ondrej Kuzelka, Yuyi Wang

Dependent randomized rounding for clustering and partition systems with knapsack constraints

David Harris, Thomas Pensyl, Aravind Srinivasan, Khoa Trinh

Noisy-Input Entropy Search for Efficient Robust Bayesian Optimization

Lukas Fröhlich, Edgar Klenske, Julia Vinogradska, Christian Daniel, Melanie Zeilinger

Deep Structured Mixtures of Gaussian Processes

Martin Trapp, Robert Peharz, Franz Pernkopf, Carl Edward Rasmussen

A Deep Generative Model for Fragment-Based Molecule Generation

Marco Podda, Davide Bacciu, Alessio Micheli

An Optimal Algorithm for Bandit Convex Optimization with Strongly-Convex and Smooth Loss

Shinji Ito

Online Learning with Continuous Variations: Dynamic Regret and Reductions

Ching-An Cheng, Jonathan Lee, Ken Goldberg, Byron Boots

Variational Autoencoders and Nonlinear ICA: A Unifying Framework

Ilyes Khemakhem, Diederik Kingma, Ricardo Monti, Aapo Hyvärinen

Improved Regret Bounds for Projection-free Bandit Convex Optimization

Dan Garber, Ben Kretzu

On the optimality of kernels for high-dimensional clustering

Leena C Vankadara, Debarghya Ghoshdastidar

Distributionally Robust Bayesian Optimization

Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka, Andreas Krause

Conditional Linear Regression

Diego Calderon, Brendan Juba, Sirui Li, Zongyi Li, Lisa Ruan

On casting importance weighted autoencoder to an EM algorithm to learn deep generative models

Dongha Kim, Jaesung Hwang, Yongdai Kim

AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC

Ruqi Zhang, A. Feder Cooper, Christopher De Sa

Learning with minibatch Wasserstein : asymptotic and gradient properties

Kilian Fatras, Younes Zine, Rémi Flamary, Remi Gribonval, Nicolas Courty

Choosing the Sample with Lowest Loss makes SGD Robust

Vatsal Shah, Xiaoxia Wu, Sujay Sanghavi

Censored Quantile Regression Forest

Alexander Hanbo Li, Jelena Bradic

Adaptive Discretization for Evaluation of Probabilistic Cost Functions

Christoph Zimmer, Danny Driess, Mona Meister, Nguyen-Tuong Duy

Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter

Wenshuo Guo, nhật Hồ, Michael Jordan

Assessing Local Generalization Capability in Deep Models

Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

Randomized Exploration in Generalized Linear Bandits

Branislav Kveton, Manzil Zaheer, Csaba Szepesvári, Lihong Li, Mohammad Ghavamzadeh

On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis

Kohei Hayashi, Masaaki Imaizumi, Yuichi Yoshida

Deontological Ethics By Monotonicity Shape Constraints

Serena Wang, Maya Gupta

Online Learning Using Only Peer Prediction

Yang Liu, Dave Helmbold

FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization

Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, Ramtin Pedarsani

Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles

Aditya Modi, Nan Jiang, Ambuj Tewari, Satinder Singh

Thompson Sampling for Linearly Constrained Bandits

Vidit Saxena, Joakim Jalden, Joseph Gonzalez

Old Dog Learns New Tricks: Randomized UCB for Bandit Problems

Sharan Vaswani, Abbas Mehrabian, Audrey Durand, Branislav Kveton

Discrete Action On-Policy Learning with Action-Value Critic

Yuguang Yue, Yunhao Tang, Mingzhang Yin, Mingyuan Zhou

DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate

Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, Mert Gurbuzbalaban

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration

Andrea Zanette, David Brandfonbrener, Emma Brunskill, Matteo Pirotta, Alessandro Lazaric

The Sylvester Graphical Lasso (SyGlasso)

Yu Wang, Byoungwook Jang, Alfred Hero

Sparse Orthogonal Variational Inference for Gaussian Processes

Jiaxin Shi, Michalis Titsias, Andriy Mnih

Distributionally Robust Bayesian Quadrature Optimization

Thanh Nguyen, Sunil Gupta, Huong Ha, Santu Rana, Svetha Venkatesh

Ensemble Gaussian Processes with Spectral Features for Online Interactive Learning with Scalability

Qin Lu, Georgios Karanikolas, Yanning Shen, Georgios B. Giannakis

RelatIF: Identifying Explanatory Training Samples via Relative Influence

Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite

Dynamical Systems Theory for Causal Inference with Application to Synthetic Control Methods

Yi Ding, Panos Toulis

Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory

Jianyi Zhang, Ruiyi Zhang, Lawrence Carin, Changyou Chen

Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models

Raaz Dwivedi, nhật Hồ, Koulik Khamaru, Martin Wainwright, Michael Jordan

Optimization Methods for Interpretable Differentiable Decision Trees Applied to Reinforcement Learning

Andrew Silva, Taylor Killian, Ivan Jimenez, Sung-Hyun Son, Matthew Gombolay

OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits

Niladri Chatterji, Vidya Muthukumar, Peter Bartlett

Learning Hierarchical Interactions at Scale: A Convex Optimization Approach

Hussein Hazimeh, Rahul Mazumder

Fixed-confidence guarantees for Bayesian best-arm identification

Xuedong Shang, Rianne Heide, Pierre Menard, Emilie Kaufmann, Michal Valko

Naive Feature Selection: Sparsity in Naive Bayes

Armin Askari, Alexandre d’Aspremont, Laurent El Ghaoui

A Rule for Gradient Estimator Selection, with an Application to Variational Inference

Tomas Geffner, Justin Domke

Validated Variational Inference via Practical Posterior Error Bounds

Jonathan Huggins, Mikolaj Kasprzak, Trevor Campbell, Tamara Broderick

The True Sample Complexity of Identifying Good Arms

Julian Katz-Samuels, Kevin Jamieson

Equalized odds postprocessing under imperfect group information

Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern

Post-Estimation Smoothing: A Simple Baseline for Learning with Side Information

Esther Rolf, Michael I. Jordan, Benjamin Recht

Coping With Simulators That Don’t Always Return

Andrew Warrington, Saeid Naderiparizi, Frank Wood

Locally Accelerated Conditional Gradients

Jelena Diakonikolas, Alejandro Carderera, Sebastian Pokutta

EM Converges for a Mixture of Many Linear Regressions

Jeongyeol Kwon, Constantine Caramanis

Langevin Monte Carlo without smoothness

Niladri Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter Bartlett

Accelerating Smooth Games by Manipulating Spectral Shapes

Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel

Spatio-temporal alignments: Optimal transport through space and time

Hicham Janati, Marco Cuturi, Alexandre Gramfort

Variational Autoencoders for Sparse and Overdispersed Discrete Data

He Zhao, Piyush Rai, Lan Du, Wray Buntine, Dinh Phung

Optimized Score Transformation for Fair Classification

Dennis Wei, Karthikeyan Natesan Ramamurthy, Flavio Calmon

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction

Boyue Li, Shicong Cen, Yuxin Chen, Yuejie Chi

GP-VAE: Deep Probabilistic Time Series Imputation

Vincent Fortuin, Dmitry Baranchuk, Gunnar Raetsch, Stephan Mandt

Value Preserving State-Action Abstractions

David Abel, Nate Umbanhowar, Khimya Khetarpal, Dilip Arumugam, Doina Precup

Revisiting the Landscape of Matrix Factorization

Hossein Valavi, Sulin Liu, Peter Ramadge

Competing Bandits in Matching Markets

Lydia T. Liu, Horia Mania, Michael Jordan

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces

David Alvarez-Melis, Youssef Mroueh, Tommi Jaakkola

DYNOTEARS: Structure Learning from Time-Series Data

Roxana Pamfil, Nisara Sriwattanaworachai, Shaan Desai, Philip Pilgerstorfer, Konstantinos Georgatzis

Automatic Differentiation of Some First-Order Methods in Parametric Optimization

Sheheryar Mehmood, Peter Ochs

Private Protocols for U-Statistics in the Local Model and Beyond

James Bell, Aurélien Bellet, Adria Gascon, Tejas Kulkarni

Differentiable Feature Selection by Discrete Relaxation

Rishit Sheth, Nicolo Fusi

A Topology Layer for Machine Learning

Rickard Brüel Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath, Primoz Skraba

Optimizing Millions of Hyperparameters by Implicit Differentiation

Jonathan Lorraine, Paul Vicol, David Duvenaud

Bayesian Image Classification with Deep Convolutional Gaussian Processes

Vincent Dutordoir, Mark Wilk, Artem Artemev, James Hensman

Decentralized Multi-player Multi-armed Bandits with No Collision Information

Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang

Bandit Convex Optimization in Non-stationary Environments

Peng Zhao, Guanghui Wang, Lijun Zhang, Zhi-Hua Zhou

A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil

Contextual Combinatorial Volatile Multi-armed Bandit with Adaptive Discretization

Andi Nika, Sepehr Elahi, Cem Tekin

Linear Convergence of Adaptive Stochastic Gradient Descent

Yuege Xie, Xiaoxia Wu, Rachel Ward

Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls

JIACHENG ZHUO, Qi Lei, Alex Dimakis, Constantine Caramanis

Regularization via Structural Label Smoothing

Weizhi Li, Gautam Dasarathy, Visar Berisha

A principled approach for generating adversarial images under non-smooth dissimilarity metrics

Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel, Adam Oberman

Conservative Exploration in Reinforcement Learning

Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta

A Multiclass Classification Approach to Label Ranking

Robin Vogel, Stéphan Clémen\con

Rep the Set: Neural Networks for Learning Set Representations

Konstantinos Skianis, Giannis Nikolentzos, Stratis Limnios, Michalis Vazirgiannis

RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization

Prathamesh Mayekar, Himanshu Tyagi

Two-sample Testing Using Deep Learning

Matthias Kirchler, Shahryar Khorasani, Marius Kloft, Christoph Lippert

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation

Si Yi Meng, Sharan Vaswani, Issam Hadj Laradji), Mark Schmidt, Simon Lacoste-Julien

Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes

Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

Sebastian Farquhar, Michael A. Osborne, Yarin Gal