AISTATS 2024

547 papers

How Good is a Single Basin?

Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann

Informative Path Planning with Limited Adaptivity

Rayen Tan, Rohan Ghuge, viswanath nagarajan

Online multiple testing with e-values

Ziyu Xu, Aaditya Ramdas

Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization

Wei Shen, Minhui Huang, Jiawei Zhang, Cong Shen

Timing as an Action: Learning When to Observe and Act

Helen Zhou, Audrey Huang, Kamyar Azizzadenesheli, David Childers, Zachary Lipton

Contextual Bandits with Budgeted Information Reveal

Kyra Gan, Esmaeil Keyvanshokooh, Xueqing Liu, Susan Murphy

Proxy Methods for Domain Adaptation

Katherine Tsai, Stephen R Pfohl, Olawale Salaudeen, Nicole Chiou, Matt Kusner

Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks

Kaiting Liu, Zahra Atashgahi, Ghada Sokar, Mykola Pechenizkiy, Decebal Constantin Mocanu

Learning Under Random Distributional Shifts

Kirk C. Bansak, Elisabeth Paulson, Dominik Rothenhaeusler

Functional Flow Matching

Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth

Membership Testing in Markov Equivalence Classes via Independence Queries

Jiaqi Zhang, Kirankumar Shiragur, Caroline Uhler

Conditions on Preference Relations that Guarantee the Existence of Optimal Policies

Jonathan Colaço Carr, Prakash Panangaden, Doina Precup

Efficient Variational Sequential Information Control

Jianwei Shen, Jason Pacheco

Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

Osama A Hanna, Merve Karakas, Lin Yang, Christina Fragouli

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent

Mehdi Jafarnia Jahromi, Rahul A Jain, Ashutosh Nayyar

Adaptive importance sampling for heavy-tailed distributions via $α$-divergence minimization

Thomas Guilmeau, Nicola Branchini, Emilie Chouzenoux, Victor Elvira

Multi-objective Optimization via Wasserstein-Fisher-Rao Gradient Flow

Yinuo Ren, Tesi Xiao, Tanmay Gangwani, Anshuka Rangi, Holakou Rahmanian

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut

Unsupervised Change Point Detection in Multivariate Time Series

Daoping Wu, Suhas Gundimeda, Shaoshuai Mou, Christopher Quinn

Fitting ARMA Time Series Models without Identification: A Proximal Approach

Yin Liu, Sam Davanloo Tajbakhsh

FairRR: Pre-Processing for Group Fairness through Randomized Response

Joshua John Ward, Xianli Zeng, Guang Cheng

On cyclical MCMC sampling

Liwei Wang, Xinru Liu, Aaron Smith, Aguemon Y Atchade

Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning

Amey P. Pasarkar, Adji Bousso Dieng

The sample complexity of ERMs in stochastic convex optimization

Daniel Carmon, Amir Yehudayoff, Roi Livni

On the Misspecification of Linear Assumptions in Synthetic Controls

Achille O. R. Nazaret, Claudia Shi, David Blei

LP-based Construction of DC Decompositions for Efficient Inference of Markov Random Fields

Chaitanya Murti, Dhruva Kashyap, Chiranjib Bhattacharyya

Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent

Jialun Zhang, Richard Y Zhang, Hong-Ming Chiu

Manifold-Aligned Counterfactual Explanations for Neural Networks

Asterios Tsiourvas, Wei Sun, Georgia Perakis

Hodge-Compositional Edge Gaussian Processes

Maosheng Yang, Viacheslav Borovitskiy, Elvin Isufi

On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective

Yipei Wang, Xiaoqian Wang

Fair Machine Unlearning: Data Removal while Mitigating Disparities

Alex Oesterling, Jiaqi Ma, Flavio Calmon, Himabindu Lakkaraju

Learning to Rank for Optimal Treatment Allocation Under Resource Constraints

Fahad Kamran, Maggie Makar, Jenna Wiens

On the Nyström Approximation for Preconditioning in Kernel Machines

Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin

Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles

Kevin Scaman, Mathieu Even, Batiste Le Bars, Laurent Massoulié

Differentially Private Conditional Independence Testing

Iden Kalemaj, Shiva Kasiviswanathan, Aaditya Ramdas

Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models

Zhao Lyu, Wai Ming Tai, Mladen Kolar, Bryon Aragam

Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities

Konstantinos Emmanouilidis, René Vidal, Nicolas Loizou

Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation

Jiayi Huang, Han Zhong, Liwei Wang, Lin Yang

Mixed Models with Multiple Instance Learning

Jan P. Engelmann, Alessandro Palma, Jakub M. Tomczak, Fabian Theis, Francesco Paolo Casale

On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions

Simon Martin, Francis Bach, Giulio Biroli

Consistent Optimal Transport with Empirical Conditional Measures

Piyushi Manupriya, Rachit K. Das, Sayantan Biswas, SakethaNath N Jagarlapudi

Dissimilarity Bandits

Paolo Battellani, Alberto Maria Metelli, Francesco Trovò

Approximate Bayesian Class-Conditional Models under Continuous Representation Shift

Thomas L. Lee, Amos Storkey

Optimal estimation of Gaussian (poly)trees

Yuhao Wang, Ming Gao, Wai Ming Tai, Bryon Aragam, Arnab Bhattacharyya

On the estimation of persistence intensity functions and linear representations of persistence diagrams

Weichen Wu, Jisu KIM, Alessandro Rinaldo

Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations

Krzysztof Kacprzyk, Mihaela van der Schaar

Equivalence Testing: The Power of Bounded Adaptivity

Diptarka Chakraborty, Sourav Chakraborty, Gunjan Kumar, Kuldeep Meel

Sequential learning of the Pareto front for multi-objective bandits

élise crepon, Aurélien Garivier, Wouter M Koolen

Identification and Estimation of “Causes of Effects” using Covariate-Mediator Information

Ryusei Shingaki, manabu kuroki

Why is parameter averaging beneficial in SGD? An objective smoothing perspective

Atsushi Nitanda, Ryuhei Kikuchi, Shugo Maeda, Denny Wu

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Hristo Papazov, Scott Pesme, Nicolas Flammarion

Length independent PAC-Bayes bounds for Simple RNNs

Volodimir Mitarchuk, Clara Lacroce, Rémi Eyraud, Rémi Emonet, Amaury Habrard

Benefits of Non-Linear Scale Parameterizations in Black Box Variational Inference through Smoothness Results and Gradient Variance Bounds

Alexandra Maria Hotti, Lennart Alexander Van der Goten, Jens Lagergren

Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation

Vinod Kumar Chauhan, Jiandong Zhou, Ghadeer Ghosheh, Soheila Molaei, David A Clifton

SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification

Patrick Kolpaczki, Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer, Eyke Hüllermeier

On learning history-based policies for controlling Markov decision processes

Gandharv Patil, Aditya Mahajan, Doina Precup

Cylindrical Thompson Sampling for High-Dimensional Bayesian Optimization

Bahador Rashidi, Kerrick Johnstonbaugh, Chao Gao

Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence

Ilyas Fatkhullin, Niao He

Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression

Kevin Li, Max Balakirsky, Simon Mak

Learning to Defer to a Population: A Meta-Learning Approach

Dharmesh Tailor, Aditya Patra, Rajeev Verma, Putra Manggala, Eric Nalisnick

Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors

Teodora Popordanoska, Sebastian Gregor Gruber, Aleksei Tiulpin, Florian Buettner, Matthew B. Blaschko

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni

Communication-Efficient Federated Learning With Data and Client Heterogeneity

Hossein Zakerinia, Shayan Talaei, Giorgi Nadiradze, Dan Alistarh

Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions

Ambrus Tamás, Szabolcs Szentpéteri, Balázs Csáji

DiffRed: Dimensionality reduction guided by stable rank

Prarabdh Shukla, Gagan Raj Gupta, Kunal Dutta

On-Demand Federated Learning for Arbitrary Target Class Distributions

Isu Jeong, Seulki Lee

Resilient Constrained Reinforcement Learning

Dongsheng Ding, Zhengyan Huan, Alejandro Ribeiro

Discriminator Guidance for Autoregressive Diffusion Models

Filip Ekström Kelvinius, Fredrik Lindsten

From Data Imputation to Data Cleaning — Automated Cleaning of Tabular Data Improves Downstream Predictive Performance

Sebastian Jäger, Felix Biessmann

DHMConv: Directed Hypergraph Momentum Convolution Framework

Wenbo Zhao, Zitong Ma, Zhe Yang

Posterior Uncertainty Quantification in Neural Networks using Data Augmentation

Luhuan Wu, Sinead A Williamson

Optimal Budgeted Rejection Sampling for Generative Models

Alexandre Verine, Muni Sreenivas Pydi, Benjamin Negrevergne, Yann Chevaleyre

ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data

Maria C. Novitasari, Johannes Quaas, Miguel Rodrigues

Score Operator Newton transport

Nisha Chandramoorthy, Florian T Schaefer, Youssef M Marzouk

Interpretable Causal Inference for Analyzing Wearable, Sensor, and Distributional Data

Srikar Katta, Harsh Parikh, Cynthia Rudin, Alexander Volfovsky

Identifiable Feature Learning for Spatial Data with Nonlinear ICA

Hermanni Hälvä, Jonathan So, Richard E. Turner, Aapo Hyvärinen

How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability

Jorge García-Carrasco, Alejandro Maté, Juan Carlos Trujillo

Don’t Be Pessimistic Too Early: Look K Steps Ahead!

Chaoqi Wang, Ziyu Ye, Kevin Murphy, Yuxin Chen

Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach

Ivan Peshekhonov, Aleksey Arzhantsev, Maxim Rakhuba

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training

Tom Sander, Maxime Sylvestre, Alain Durmus

Variational Resampling

Oskar Kviman, Nicola Branchini, Victor Elvira, Jens Lagergren

Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation

Zhi Zhang, Chenyu Ma, Saleh Soudijani, Sadegh Soudjani

Directed Hypergraph Representation Learning for Link Prediction

Zitong Ma, Wenbo Zhao, Zhe Yang

SDMTR: A Brain-inspired Transformer for Relation Inference

Xiangyu Zeng, Jie Lin, Piao Hu, Zhihao Li, Tianxi Huang

Model-based Policy Optimization under Approximate Bayesian Inference

Chaoqi Wang, Yuxin Chen, Kevin Murphy

Learning multivariate temporal point processes via the time-change theorem

Guilherme Augusto Zagatti, See Kiong Ng, Stéphane Bressan

No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints

Arpan Losalka, Jonathan Scarlett

On Feynman-Kac training of partial Bayesian neural networks

Zheng Zhao, Sebastian Mair, Thomas B. Schön, Jens Sjölund

Symmetric Equilibrium Learning of VAEs

Boris Flach, Dmitrij Schlesinger, Alexander Shekhovtsov

General Tail Bounds for Non-Smooth Stochastic Mirror Descent

Khaled Eldowa, Andrea Paudice

XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage

Jae-Jun Lee, Sung Whan Yoon

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data

Yuqin Yang, Saber Salehkaleybar, Negar Kiyavash

Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity

Vincent Souveton, Arnaud Guillin, Jens Jasche, Guilhem Lavaux, Manon Michel

Offline Primal-Dual Reinforcement Learning for Linear MDPs

Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka M Okolo

Approximate Control for Continuous-Time POMDPs

Yannick Eich, Bastian Alt, Heinz Koeppl

A Scalable Algorithm for Individually Fair k-Means Clustering

Mohammadhossein Bateni, Vincent Cohen-Addad, Alessandro Epasto, Silvio Lattanzi

Multi-Agent Learning in Contextual Games under Unknown Constraints

Anna M. Maddux, Maryam Kamgarpour

Probabilistic Calibration by Design for Neural Network Regression

Victor Dheur, Souhaib Ben Taieb

Causally Inspired Regularization Enables Domain General Representations

Olawale Salaudeen, Sanmi Koyejo