AISTATS 2024

547 papers

Testing exchangeability by pairwise betting

Aytijhya Saha, Aaditya Ramdas

Tight Verification of Probabilistic Robustness in Bayesian Neural Networks

Ben Batten, Mehran Hosseini, Alessio Lomuscio

Identifying Confounding from Causal Mechanism Shifts

Sarah Mameche, Jilles Vreeken, David Kaltenpoth

Sample-efficient neural likelihood-free Bayesian inference of implicit HMMs

Sanmitra Ghosh, Paul Birrell, Daniela De Angelis

Efficient Conformal Prediction under Data Heterogeneity

Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov

Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases

Ruslan Nazykov, Aleksandr Shestakov, Vladimir Solodkin, Aleksandr Beznosikov, Gauthier Gidel

Parameter-Agnostic Optimization under Relaxed Smoothness

Florian Hübler, Junchi Yang, Xiang Li, Niao He

Differentiable Rendering with Reparameterized Volume Sampling

Nikita Morozov, Denis Rakitin, Oleg Desheulin, Dmitry P Vetrov, Kirill Struminsky

Differentially Private Reward Estimation with Preference Feedback

Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan

SDEs for Minimax Optimization

Enea Monzio Compagnoni, Antonio Orvieto, Hans Kersting, Frank Proske, Aurelien Lucchi

Consistent Hierarchical Classification with A Generalized Metric

Yuzhou Cao, Lei Feng, Bo An

Mitigating Underfitting in Learning to Defer with Consistent Losses

Shuqi Liu, Yuzhou Cao, Qiaozhen Zhang, Lei Feng, Bo An

Random Oscillators Network for Time Series Processing

Andrea Ceni, Andrea Cossu, Maximilian W Stölzle, Jingyue Liu, Cosimo Della Santina

Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains

Nikita Tsoy, Anna Mihalkova, Teodora N Todorova, Nikola Konstantinov

Warped Diffusion for Latent Differentiation Inference

Masahiro Nakano, Hiroki Sakuma, Ryo Nishikimi, Ryohei Shibue, Takashi Sato

Revisiting the Noise Model of Stochastic Gradient Descent

Barak Battash, Lior Wolf, Ofir Lindenbaum

Data Driven Threshold and Potential Initialization for Spiking Neural Networks

Velibor Bojkovic, Srinivas Anumasa, Giulia De Masi, Bin Gu, Huan Xiong

Deep Classifier Mimicry without Data Access

Steven Braun, Martin Mundt, Kristian Kersting

Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention

Anqi Mao, Mehryar Mohri, Yutao Zhong

Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach

Yinan Li, Chicheng Zhang

Sharpened Lazy Incremental Quasi-Newton Method

Aakash Sunil Lahoti, Spandan Senapati, Ketan Rajawat, Alec Koppel

Understanding Inverse Scaling and Emergence in Multitask Representation Learning

Muhammed E. Ildiz, Zhe Zhao, Samet Oymak

Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach

Juanwu Lu, Wei Zhan, Masayoshi Tomizuka, Yeping Hu

A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning

Mizhaan P. Maniyar, Prashanth L.A., Akash Mondal, Shalabh Bhatnagar

Provable Policy Gradient Methods for Average-Reward Markov Potential Games

Min Cheng, Ruida Zhou, P. R. Kumar, Chao Tian

Faster Recalibration of an Online Predictor via Approachability

Princewill Okoroafor, Bobby Kleinberg, Wen Sun

On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: a regret lower bound for WSU-UX

Ali Mortazavi, Junhao Lin, Nishant Mehta

Mixture-of-Linear-Experts for Long-term Time Series Forecasting

Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti

Adaptive Federated Minimax Optimization with Lower Complexities

Feihu Huang, Xinrui Wang, Junyi Li, Songcan Chen

The ALℓ_0CORE Tensor Decomposition for Sparse Count Data

John Hood, Aaron J. Schein

Pathwise Explanation of ReLU Neural Networks

Seongwoo Lim, Won Jo, Joohyung Lee, Jaesik Choi

Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs

Mishfad Shaikh Veedu, Deepjyoti Deka, Murti Salapaka

Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints

Ahmet Alacaoglu, Stephen J Wright

Surrogate Active Subspaces for Jump-Discontinuous Functions

Nathan Wycoff

Causal Bandits with General Causal Models and Interventions

Zirui Yan, Dennis Wei, Dmitriy A Katz, Prasanna Sattigeri, Ali Tajer

autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm

Miguel Biron-Lattes, Nikola Surjanovic, Saifuddin Syed, Trevor Campbell, Alexandre Bouchard-côté

Sample Efficient Learning of Factored Embeddings of Tensor Fields

Taemin Heo, Chandrajit Bajaj

Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process

Lingkai Kong, Haotian Sun, Yuchen Zhuang, Haorui Wang, Wenhao Mu

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models

Cyrus Cousins, I. Elizabeth Kumar, Suresh Venkatasubramanian

Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty

Yu Inatsu, Shion Takeno, Hiroyuki Hanada, Kazuki Iwata, Ichiro Takeuchi

Fast Fourier Bayesian Quadrature

Houston Warren, Fabio Ramos

Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources

Rohan Deb, Aadirupa Saha, Arindam Banerjee

BLIS-Net: Classifying and Analyzing Signals on Graphs

Charles Xu, Laney Goldman, Valentina Guo, Benjamin Hollander-Bodie, Maedee Trank-Greene

Non-vacuous Generalization Bounds for Adversarial Risk in Stochastic Neural Networks

Waleed Mustafa, Philipp Liznerski, Antoine Ledent, Dennis Wagner, Puyu Wang

On the Generalization Ability of Unsupervised Pretraining

Yuyang Deng, Junyuan Hong, Jiayu Zhou, Mehrdad Mahdavi

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective

Bhagyashree Puranik, Ahmad Beirami, Yao Qin, Upamanyu Madhow

Gibbs-Based Information Criteria and the Over-Parameterized Regime

Haobo Chen, Gregory W Wornell, Yuheng Bu

Identifiability of Product of Experts Models

Manav Kant, Eric Y Ma, Andrei Staicu, Leonard J Schulman, Spencer Gordon

Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization

Yutong Wang, Rishi Sonthalia, Wei Hu

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion

Junghyun Lee, Se-Young Yun, Kwang-Sung Jun

Understanding the Generalization Benefits of Late Learning Rate Decay

Yinuo Ren, Chao Ma, Lexing Ying

Policy Learning for Localized Interventions from Observational Data

Myrl G. Marmarelis, Fred Morstatter, Aram Galstyan, Greg Ver Steeg

A General Theoretical Paradigm to Understand Learning from Human Preferences

Mohammad Gheshlaghi azar, Zhaohan Daniel Guo, Bilal Piot, Rémi Munos, Mark Rowland

Coreset Markov chain Monte Carlo

Naitong Chen, Trevor Campbell

Soft-constrained Schrödinger Bridge: a Stochastic Control Approach

Jhanvi Garg, Xianyang Zhang, Quan Zhou

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

Wesley Suttle, Vipul Kumar Sharma, Krishna Chaitanya Kosaraju, Sivaranjani Seetharaman, Ji Liu

Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate

Ruichen Jiang, Parameswaran Raman, Shoham Sabach, Aryan Mokhtari, Mingyi Hong

Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate

Hongchang Gao

The effect of Leaky ReLUs on the training and generalization of overparameterized networks

Yinglong Guo, Shaohan Li, Gilad Lerman

FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning

Xiang Meng, Wenyu Chen, Riade Benbaki, Rahul Mazumder

Self-Supervised Quantization-Aware Knowledge Distillation

Kaiqi Zhao, Ming Zhao

Causal Q-Aggregation for CATE Model Selection

Hui Lan, Vasilis Syrgkanis

Probabilistic Modeling for Sequences of Sets in Continuous-Time

Yuxin Chang, Alex J Boyd, Padhraic Smyth

Consistency of Dictionary-Based Manifold Learning

Samson J. Koelle, Hanyu Zhang, Octavian-Vlad Murad, Marina Meila

Auditing Fairness under Unobserved Confounding

Yewon Byun, Dylan Sam, Michael Oberst, Zachary Lipton, Bryan Wilder

Tensor-view Topological Graph Neural Network

Tao Wen, Elynn Chen, Yuzhou Chen

Anytime-Constrained Reinforcement Learning

Jeremy McMahan, Xiaojin Zhu

Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference

Declan McNamara, Jackson Loper, Jeffrey Regier

Computing epidemic metrics with edge differential privacy

George Z. Li, Dung Nguyen, Anil Vullikanti

Asynchronous Randomized Trace Estimation

Vasileios Kalantzis, Shashanka Ubaru, Chai Wah Wu, Georgios Kollias, Lior Horesh

Benchmarking Observational Studies with Experimental Data under Right-Censoring

Ilker Demirel, Edward De Brouwer, Zeshan M Hussain, Michael Oberst, Anthony A Philippakis

Towards Practical Non-Adversarial Distribution Matching

ZIYU GONG, Ben Usman, Han Zhao, David I Inouye

Simulation-Based Stacking

Yuling Yao, Bruno Régaldo-Saint Blancard, Justin Domke

DE-HNN: An effective neural model for Circuit Netlist representation

Zhishang Luo, Truong Son Hy, Puoya Tabaghi, Michaël Defferrard, Elahe Rezaei

The Effective Number of Shared Dimensions Between Paired Datasets

Hamza Giaffar, Camille Rullán Buxó, Mikio Aoi

User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates

Daogao Liu, Hilal Asi

First Passage Percolation with Queried Hints

Kritkorn Karntikoon, Yiheng Shen, Sreenivas Gollapudi, Kostas Kollias, Aaron Schild

Multi-resolution Time-Series Transformer for Long-term Forecasting

Yitian Zhang, Liheng Ma, Soumyasundar Pal, Yingxue Zhang, Mark Coates

Generative Flow Networks as Entropy-Regularized RL

Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry P Vetrov

Weight-Sharing Regularization

Mehran Shakerinava, Motahareh MS Sohrabi, Siamak Ravanbakhsh, Simon Lacoste-Julien

Zongyu Dai, Emily Getzen, Qi Long

Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm

Mohammad Reza Karimi, Ya-Ping Hsieh, Andreas Krause

Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems

Neharika Jali, Guannan Qu, Weina Wang, Gauri Joshi

Towards a Complete Benchmark on Video Moment Localization

Jinyeong Chae, Donghwa Kim, Kwanseok Kim, Doyeon Lee, Sangho Lee

An Improved Algorithm for Learning Drifting Discrete Distributions

Alessio Mazzetto

Private Learning with Public Features

Walid Krichene, Nicolas E Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta

Equivariant bootstrapping for uncertainty quantification in imaging inverse problems

Marcelo Pereyra, Julián Tachella

Self-Compatibility: Evaluating Causal Discovery without Ground Truth

Philipp M. Faller, Leena C. Vankadara, Atalanti A. Mastakouri, Francesco Locatello, Dominik Janzing

Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements

Emmanouil Vasileios Vlatakis-Gkaragkounis, Angeliki Giannou, Yudong Chen, Qiaomin Xie

Think Global, Adapt Local: Learning Locally Adaptive K-Nearest Neighbor Kernel Density Estimators

Kenny Olsen, Rasmus M. Hoeegh Lindrup, Morten Mørup

Uncertainty-aware Continuous Implicit Neural Representations for Remote Sensing Object Counting

Siyuan Xu, Yucheng Wang, Mingzhou Fan, Byung-Jun Yoon, Xiaoning Qian

On the Vulnerability of Fairness Constrained Learning to Malicious Noise

Avrim Blum, Princewill Okoroafor, Aadirupa Saha, Kevin M. Stangl

An Analytic Solution to Covariance Propagation in Neural Networks

Oren Wright, Yorie Nakahira, José M. F. Moura

Deep Learning-Based Alternative Route Computation

Alex Zhai, Dee Guo, Sreenivas Gollapudi, Kostas Kollias, Daniel Delling

Low-rank MDPs with Continuous Action Spaces

Miruna Oprescu, Andrew Bennett, Nathan Kallus

Acceleration and Implicit Regularization in Gaussian Phase Retrieval

Tyler Maunu, Martin Molina-Fructuoso

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami

Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection

Mohammad Mahmudul Alam, Edward Raff, Stella R Biderman, Tim Oates, James Holt

NoisyMix: Boosting Model Robustness to Common Corruptions

Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Francisco Utrera, Ziang Cao

Independent Learning in Constrained Markov Potential Games

Philip Jordan, Anas Barakat, Niao He