AISTATS 2023

496 papers

Efficient SAGE Estimation via Causal Structure Learning

Christoph Luther, Gunnar König, Moritz Grosse-wentrup

Probing Graph Representations

Mohammad Sadegh Akhondzadeh, Vijay Lingam, Aleksandar Bojchevski

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond

meyer scetbon, Elvis DOHMATOB

Regression as Classification: Influence of Task Formulation on Neural Network Features

Lawrence Stewart, Francis Bach, Quentin Berthet, Jean-philippe Vert

Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity

Arber Qoku, Florian Buettner

Inducing Neural Collapse in Deep Long-tailed Learning

Xuantong Liu, Jianfeng Zhang, Tianyang Hu, He CAO, Yuan Yao

Algorithm for Constrained Markov Decision Process with Linear Convergence

Egor Gladin, Maksim Lavrik-Karmazin, Karina Zainullina, Varvara Rudenko, Alexander Gasnikov

Characterizing Polarization in Social Networks using the Signed Relational Latent Distance Model

Nikolaos Nakis, Abdulkadir Çelikkanat, Louis Boucherie, Christian Djurhuus, Felix Burmester

Breaking a Classical Barrier for Classifying Arbitrary Test Examples in the Quantum Model

Grzegorz Gluch, Khashayar Barooti, Rüdiger Urbanke

Spread Flows for Manifold Modelling

Mingtian Zhang, Yitong Sun, Chen Zhang, Steven McDonagh

Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles

Rajeev Verma, Daniel Barrejon, Eric Nalisnick

Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves

David Bosch, Ashkan Panahi, Ayca Ozcelikkale, Devdatt Dubhashi

Collision Probability Matching Loss for Disentangling Epistemic Uncertainty from Aleatoric Uncertainty

Hiromi Narimatsu, Mayuko Ozawa, Shiro Kumano

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

Sebastian Gruber, Florian Buettner

Average case analysis of Lasso under ultra sparse conditions

Koki Okajima, Xiangming Meng, Takashi Takahashi, Yoshiyuki Kabashima

Optimal Sketching Bounds for Sparse Linear Regression

Tung Mai, Alexander Munteanu, Cameron Musco, Anup Rao, Chris Schwiegelshohn

Deep Value Function Networks for Large-Scale Multistage Stochastic Programs

Hyunglip Bae, Jinkyu Lee, Woo Chang Kim, Yongjae Lee

Spectral Augmentations for Graph Contrastive Learning

Amur Ghose, Yingxue Zhang, Jianye Hao, Mark Coates

Randomized Primal-Dual Methods with Adaptive Step Sizes

Erfan Yazdandoost Hamedani, Afrooz Jalilzadeh, Necdet S. Aybat

Approximate Regions of Attraction in Learning with Decision-Dependent Distributions

Roy Dong, Heling Zhang, Lillian Ratliff

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation

Jackie Baek, Vivek Farias

A New Modeling Framework for Continuous, Sequential Domains

Hailiang Dong, James Amato, Vibhav Gogate, Nicholas Ruozzi

Benign overfitting of non-smooth neural networks beyond lazy training

Xingyu Xu, Yuantao Gu

Performative Prediction with Neural Networks

Mehrnaz Mofakhami, Ioannis Mitliagkas, Gauthier Gidel

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes

Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn, Zico Kolter

Mixtures of All Trees

Nikil Roashan Selvam, Honghua Zhang, Guy Van den Broeck

Posterior Tracking Algorithm for Classification Bandits

Koji Tabata, Junpei Komiyama, Atsuyoshi Nakamura, Tamiki Komatsuzaki

A Blessing of Dimensionality in Membership Inference through Regularization

Jasper Tan, Daniel LeJeune, Blake Mason, Hamid Javadi, Richard G. Baraniuk

Provable Hierarchy-Based Meta-Reinforcement Learning

Kurtland Chua, Qi Lei, Jason Lee

Balanced Off-Policy Evaluation for Personalized Pricing

Adam Elmachtoub, Vishal Gupta, Yunfan Zhao

Provable Safe Reinforcement Learning with Binary Feedback

Andrew Bennett, Dipendra Misra, Nathan Kallus

Uniformly Conservative Exploration in Reinforcement Learning

Wanqiao Xu, Yecheng Ma, Kan Xu, Hamsa Bastani, Osbert Bastani

Convolutional Persistence as a Remedy to Neural Model Analysis

Ekaterina Khramtsova, Guido Zuccon, Xi Wang, Mahsa Baktashmotlagh

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data

Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, CHRISTOS THRAMPOULIDIS

Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees

Joseph Janssen, Vincent Guan, Elina Robeva

HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent

Ziang Chen, Jianfeng Lu, Huajie Qian, Xinshang Wang, Wotao Yin

Wasserstein Distributional Learning via Majorization-Minimization

Chengliang Tang, Nathan Lenssen, Ying Wei, Tian Zheng

Conformalized Unconditional Quantile Regression

Ahmed M. Alaa, Zeshan Hussain, David Sontag

Federated Asymptotics: a model to compare federated learning algorithms

Gary Cheng, Karan Chadha, John Duchi

Reinforcement Learning with Stepwise Fairness Constraints

Zhun Deng, He Sun, Steven Wu, Linjun Zhang, David Parkes

Dropout-Resilient Secure Multi-Party Collaborative Learning with Linear Communication Complexity

Xingyu Lu, Hasin Us Sami, Basak Guler

Score-based Quickest Change Detection for Unnormalized Models

Suya Wu, Enmao Diao, Taposh Banerjee, Jie Ding, Vahid Tarokh

Graph Spectral Embedding using the Geodesic Betweenness Centrality

Shay Deutsch, Stefano Soatto

Sample Complexity of Distinguishing Cause from Effect

Jayadev Acharya, Sourbh Bhadane, Arnab Bhattacharyya, Saravanan Kandasamy, Ziteng Sun

Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions

Kaiqi Zhao, Animesh Jain, Ming Zhao

Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier

Spencer Compton, Dmitriy Katz, Benjamin Qi, Kristjan Greenewald, Murat Kocaoglu

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

Matthew D. Hoffman, Tuan Anh Le, Pavel Sountsov, Christopher Suter, Ben Lee

Competing against Adaptive Strategies in Online Learning via Hints

Aditya Bhaskara, Kamesh Munagala

Actually Sparse Variational Gaussian Processes

Harry Jake Cunningham, Daniel Augusto de Souza, So Takao, Mark van der Wilk, Marc Peter Deisenroth

Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation

Qi Chen, Mario Marchand

DIET: Conditional independence testing with marginal dependence measures of residual information

Mukund Sudarshan, Aahlad Puli, Wesley Tansey, Rajesh Ranganath

Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints

Yao Yao, Qihang Lin, Tianbao Yang

A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem

Ruichen Jiang, Nazanin Abolfazli, Aryan Mokhtari, Erfan Yazdandoost Hamedani

SurvivalGAN: Generating Time-to-Event Data for Survival Analysis

Alexander Norcliffe, Bogdan Cebere, Fergus Imrie, Pietro Lió, Mihaela van der Schaar

Fast Variational Estimation of Mutual Information for Implicit and Explicit Likelihood Models

Caleb Dahlke, Sue Zheng, Jason Pacheco

Semantic Strengthening of Neuro-Symbolic Learning

Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck

Probabilistic Querying of Continuous-Time Event Sequences

Alex Boyd, Yuxin Chang, Stephan Mandt, Padhraic Smyth

Ideal Abstractions for Decision-Focused Learning

Michael Poli, Stefano Massaroli, Stefano Ermon, Bryan Wilder, Eric Horvitz

Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck

Anirban Samaddar, Sandeep Madireddy, Prasanna Balaprakash, Taps Maiti, Gustavo de los Campos

Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path

Muhammad Aneeq Uz Zaman, Alec Koppel, Sujay Bhatt, Tamer Basar

Improving Adaptive Conformal Prediction Using Self-Supervised Learning

Nabeel Seedat, Alan Jeffares, Fergus Imrie, Mihaela van der Schaar

Stochastic Optimization for Spectral Risk Measures

Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zaïd Harchaoui

Large deviations rates for stochastic gradient descent with strongly convex functions

Dragana Bajovic, Dusan Jakovetic, Soummya Kar

Theoretically Grounded Loss Functions and Algorithms for Adversarial Robustness

Pranjal Awasthi, Anqi Mao, Mehryar Mohri, Yutao Zhong

Influence Diagnostics under Self-concordance

Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zaïd Harchaoui

Probabilities of Causation: Role of Observational Data

Ang Li, Judea Pearl

Doubly Fair Dynamic Pricing

Jianyu Xu, Dan Qiao, Yu-Xiang Wang

Near-Optimal Differentially Private Reinforcement Learning

Dan Qiao, Yu-Xiang Wang

Iterative Teaching by Data Hallucination

Zeju Qiu, Weiyang Liu, Tim Z. Xiao, Zhen Liu, Umang Bhatt

Precision/Recall on Imbalanced Test Data

Hongwei Shang, Jean-Marc Langlois, Kostas Tsioutsiouliklis, Changsung Kang

On The Convergence Of Policy Iteration-Based Reinforcement Learning With Monte Carlo Policy Evaluation

Anna Winnicki, R. Srikant

Theory and Algorithm for Batch Distribution Drift Problems

Pranjal Awasthi, Corinna Cortes, Christopher Mohri

Learning to Generalize Provably in Learning to Optimize

Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He, Dacheng Tao

Interactive Learning with Pricing for Optimal and Stable Allocations in Markets

Yigit Efe Erginbas, Soham Phade, Kannan Ramchandran

Factorial SDE for Multi-Output Gaussian Process Regression

Daniel P. Jeong, Seyoung Kim

Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning

Zaiyan Xu, Kishan Panaganti, Dileep Kalathil

Reducing Discretization Error in the Frank-Wolfe Method

Zhaoyue Chen, Yifan Sun

On the Privacy Risks of Algorithmic Recourse

Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel

Adapting to Latent Subgroup Shifts via Concepts and Proxies

Ibrahim Alabdulmohsin, Nicole Chiou, Alexander D’Amour, Arthur Gretton, Sanmi Koyejo

Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games

Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang

Domain Adaptation under Missingness Shift

Helen Zhou, Sivaraman Balakrishnan, Zachary Lipton

MMD-B-Fair: Learning Fair Representations with Statistical Testing

Namrata Deka, Danica J. Sutherland

Diffusion Generative Models in Infinite Dimensions

Gavin Kerrigan, Justin Ley, Padhraic Smyth

Improved Approximation for Fair Correlation Clustering

Sara Ahmadian, Maryam Negahbani

Compositional Probabilistic and Causal Inference using Tractable Circuit Models

Benjie Wang, Marta Kwiatkowska

Multiple-policy High-confidence Policy Evaluation

Chris Dann, Mohammad Ghavamzadeh, Teodor V. Marinov

Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games

Arnab Maiti, Kevin Jamieson, Lillian Ratliff

ForestPrune: Compact Depth-Pruned Tree Ensembles

Brian Liu, Rahul Mazumder

Randomized geometric tools for anomaly detection in stock markets

Cyril Bachelard, Apostolos Chalkis, Vissarion Fisikopoulos, Elias Tsigaridas

Optimal robustness-consistency tradeoffs for learning-augmented metrical task systems

Nicolas Christianson, Junxuan Shen, Adam Wierman

Coherent Probabilistic Forecasting of Temporal Hierarchies

Syama Sundar Rangapuram, Shubham Kapoor, Rajbir Singh Nirwan, Pedro Mercado, Tim Januschowski

Incentive-aware Contextual Pricing with Non-parametric Market Noise

Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang

Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining

Nicholas Monath, Manzil Zaheer, Kelsey Allen, Andrew McCallum

Pricing against a Budget and ROI Constrained Buyer

Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang, Vahab Mirrokni

On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network

Hongchang Gao, Bin Gu, My T. Thai

A Mini-Block Fisher Method for Deep Neural Networks

Achraf Bahamou, Donald Goldfarb, Yi Ren

SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval

Minyoung Kim

Krylov–Bellman boosting: Super-linear policy evaluation in general state spaces

Eric Xia, Martin Wainwright

Active Cost-aware Labeling of Streaming Data

Ting Cai, Kirthevasan Kandasamy