AISTATS 2024

547 papers

Online learning in bandits with predicted context

Yongyi Guo, Ziping Xu, Susan Murphy

Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent

Bianca M. Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane

Free-form Flows: Make Any Architecture a Normalizing Flow

Felix Draxler, Peter Sorrenson, Lea Zimmermann, Armand Rousselot, Ullrich Köthe

Quantifying intrinsic causal contributions via structure preserving interventions

Dominik Janzing, Patrick Blöbaum, Atalanti A Mastakouri, Philipp M Faller, Lenon Minorics

On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers

Cai Zhou, Rose Yu, Yusu Wang

Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures

Mingyuan Zhang, Shivani Agarwal

Understanding Progressive Training Through the Framework of Randomized Coordinate Descent

Rafał Szlendak, Elnur Gasanov, Peter Richtarik

Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games

Martino Bernasconi, Alberto Marchesi, Francesco Trovò

Probabilistic Integral Circuits

Gennaro Gala, Cassio de Campos, Robert Peharz, Antonio Vergari, Erik Quaeghebeur

Safe and Interpretable Estimation of Optimal Treatment Regimes

Harsh Parikh, Quinn M Lanners, Zade Akras, Sahar Zafar, M Brandon Westover

Enhancing Distributional Stability among Sub-populations

Jiashuo Liu, Jiayun Wu, Jie Peng, Xiaoyu Wu, Yang Zheng

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

Haoyue Tang, Tian Xie, Aosong Feng, Hanyu Wang, Chenyang Zhang

Robust Approximate Sampling via Stochastic Gradient Barker Dynamics

Lorenzo Mauri, Giacomo Zanella

Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses

Shiliang Zuo

Learning Sparse Codes with Entropy-Based ELBOs

Dmytro Velychko, Simon Damm, Asja Fischer, Jörg Lücke

Extragradient Type Methods for Riemannian Variational Inequality Problems

Zihao Hu, Guanghui Wang, Xi Wang, Andre Wibisono, Jacob D Abernethy

Sparse and Faithful Explanations Without Sparse Models

Yiyang Sun, Zhi Chen, Vittorio Orlandi, Tong Wang, Cynthia Rudin

On Convergence in Wasserstein Distance and f-divergence Minimization Problems

Cheuk Ting Li, Jingwei Zhang, Farzan Farnia

GmGM: a fast multi-axis Gaussian graphical model

Ethan B. Andrew, David Westhead, Luisa Cutillo

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games

Jing Dong, Baoxiang Wang, Yaoliang Yu

RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model

Junyi Fan, Yuxuan Han, Jialin Zeng, Jian-Feng CAI, Yang Wang

Training Implicit Generative Models via an Invariant Statistical Loss

José Manuel de Frutos, Pablo Olmos, Manuel Alberto Vazquez Lopez, Joaquín Míguez

Tackling the XAI Disagreement Problem with Regional Explanations

Gabriel Laberge, Yann Batiste Pequignot, Mario Marchand, Foutse Khomh

Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method

Jiulin Wang, Xu Shi, Rujun Jiang

Vector Quantile Regression on Manifolds

Marco Pegoraro, Sanketh Vedula, Aviv A Rosenberg, Irene Tallini, Emanuele Rodolà

An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization

Lesi Chen, Haishan Ye, Luo Luo

Scalable Meta-Learning with Gaussian Processes

Petru Tighineanu, Lukas Grossberger, Paul Baireuther, Kathrin Skubch, Stefan Falkner

Classifier Calibration with ROC-Regularized Isotonic Regression

Eugène Berta, Francis Bach, Michael Jordan

Interpretability Guarantees with Merlin-Arthur Classifiers

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta

Ethics in Action: Training Reinforcement Learning Agents for Moral Decision-making In Text-based Adventure Games

Weichen Li, Rati Devidze, Waleed Mustafa, Sophie Fellenz

A 4-Approximation Algorithm for Min Max Correlation Clustering

Holger S. G. Heidrich, Jannik Irmai, Bjoern Andres

Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing

Yuma Ichikawa, Koji Hukushima

Causal Modeling with Stationary Diffusions

Lars Lorch, Andreas Krause, Bernhard Schölkopf

Positivity-free Policy Learning with Observational Data

Pan Zhao, Antoine Chambaz, Julie Josse, Shu Yang

Variational Gaussian Process Diffusion Processes

Prakhar Verma, Vincent ADAM, Arno Solin

Restricted Isometry Property of Rank-One Measurements with Random Unit-Modulus Vectors

Wei Zhang, Zhenni Wang

Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks

Marcus A. K. September, Francesco Sanna Passino, Leonie Goldmann, Anton Hinel

Time to Cite: Modeling Citation Networks using the Dynamic Impact Single-Event Embedding Model

Nikolaos Nakis, Abdulkadir Çelikkanat, Louis Boucherie, Sune Lehmann, Morten Mørup

Bures-Wasserstein Means of Graphs

Isabel Haasler, Pascal Frossard

DAGnosis: Localized Identification of Data Inconsistencies using Structures

Nicolas Huynh, Jeroen Berrevoets, Nabeel Seedat, Jonathan Crabbe, Zhaozhi Qian

Structural perspective on constraint-based learning of Markov networks

Tuukka Korhonen, Fedor Fomin, Pekka Parviainen

Multitask Online Learning: Listen to the Neighborhood Buzz

Juliette Achddou, Nicolò Cesa-bianchi, Pierre Laforgue

Provable local learning rule by expert aggregation for a Hawkes network

Sophie Jaffard, Samuel Vaiter, Alexandre Muzy, Patricia Reynaud-Bouret

CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference

Vo Nguyen Le Duy, Hsuan-tien Lin, Ichiro Takeuchi

Bayesian Semi-structured Subspace Inference

Daniel Dold, David Ruegamer, Beate Sick, Oliver Dürr

Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting

Louis Sharrock, Daniel Dodd, Christopher Nemeth

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing

Dominik Wagner, Basim Khajwal, Luke Ong

On The Temporal Domain of Differential Equation Inspired Graph Neural Networks

Moshe Eliasof, Eldad Haber, Eran Treister, Carola-Bibiane B Schönlieb

Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean

Anton Frederik Thielmann, René-Marcel Kruse, Thomas Kneib, Benjamin Säfken

Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures

Hao Liang, Zhiquan Luo

Robust SVD Made Easy: A fast and reliable algorithm for large-scale data analysis

Sangil Han, Sungkyu Jung, Kyoowon Kim

Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation

Tong Wu

Analysis of Using Sigmoid Loss for Contrastive Learning

Chungpa Lee, Joonhwan Chang, Jy-yong Sohn

Efficient Neural Architecture Design via Capturing Architecture-Performance Joint Distribution

Yue Liu, Ziyi Yu, Zitu Liu, Wenjie Tian

A Neural Architecture Predictor based on GNN-Enhanced Transformer

Xunzhi Xiang, Kun Jing, Jungang Xu

Learning Populations of Preferences via Pairwise Comparison Queries

Gokcan Tatli, Yi Chen, Ramya Korlakai Vinayak

Queuing dynamics of asynchronous Federated Learning

Louis Leconte, Matthieu Jonckheere, Sergey Samsonov, Eric Moulines

Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components

Soumyabrata Pal, Prateek Varshney, Gagan Madan, Prateek Jain, Abhradeep Thakurta

Sample Complexity Characterization for Linear Contextual MDPs

Junze Deng, Yuan Cheng, Shaofeng Zou, Yingbin Liang

Optimal Exploration is no harder than Thompson Sampling

Zhaoqi Li, Kevin Jamieson, Lalit Jain

Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning

Zeqi Ye, Hansheng Jiang

Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex

Yasushi Esaki, Akihiro Nakamura, Keisuke Kawano, Ryoko Tokuhisa, Takuro Kutsuna

Conformalized Deep Splines for Optimal and Efficient Prediction Sets

Nathaniel Diamant, Ehsan Hajiramezanali, Tommaso Biancalani, Gabriele Scalia

Adaptivity of Diffusion Models to Manifold Structures

Rong Tang, Yun Yang

Joint control variate for faster black-box variational inference

Xi Wang, Tomas Geffner, Justin Domke

Feasible Q-Learning for Average Reward Reinforcement Learning

Ying Jin, Ramki Gummadi, Zhengyuan Zhou, Jose Blanchet

Causal Discovery under Off-Target Interventions

Davin Choo, Kirankumar Shiragur, Caroline Uhler

FedFisher: Leveraging Fisher Information for One-Shot Federated Learning

Divyansh Jhunjhunwala, Shiqiang Wang, Gauri Joshi

Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses

Ziye Ma, Ying Chen, Javad Lavaei, Somayeh Sojoudi

Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes

Jinwon Sohn, Qifan Song, Guang Lin

A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity

Zhihan Xiong, Romain Camilleri, Maryam Fazel, Lalit Jain, Kevin Jamieson

Thompson Sampling Itself is Differentially Private

Tingting Ou, Rachel Cummings, Marco Avella Medina

Model-Based Best Arm Identification for Decreasing Bandits

Sho Takemori, Yuhei Umeda, Aditya Gopalan

Estimation of partially known Gaussian graphical models with score-based structural priors

Martín Sevilla, Antonio G. Marques, Santiago Segarra

On the Expected Size of Conformal Prediction Sets

Guneet S. Dhillon, George Deligiannidis, Tom Rainforth

Integrating Uncertainty Awareness into Conformalized Quantile Regression

Raphael Rossellini, Rina Foygel Barber, Rebecca Willett

Data-Driven Online Model Selection With Regret Guarantees

Chris Dann, Claudio Gentile, Aldo Pacchiano

On Counterfactual Metrics for Social Welfare: Incentives, Ranking, and Information Asymmetry

Serena Wang, Stephen Bates, P Aronow, Michael Jordan

Learning Latent Partial Matchings with Gumbel-IPF Networks

Hedda Cohen Indelman, Tamir Hazan

Transductive conformal inference with adaptive scores

Ulysse Gazin, Gilles Blanchard, Etienne Roquain

On the Privacy of Selection Mechanisms with Gaussian Noise

Jonathan Lebensold, Doina Precup, Borja Balle

Taming False Positives in Out-of-Distribution Detection with Human Feedback

Harit Vishwakarma, Heguang Lin, Ramya Korlakai Vinayak

Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications

Jie Hu, Vishwaraj Doshi, Do Young Eun

Confident Feature Ranking

Bitya Neuhof, Yuval Benjamini

Offline Policy Evaluation and Optimization Under Confounding

Chinmaya Kausik, Yangyi Lu, Kevin Tan, Maggie Makar, Yixin Wang

Online Calibrated and Conformal Prediction Improves Bayesian Optimization

Shachi Deshpande, Charles Marx, Volodymyr Kuleshov

Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation

Qing En, Yuhong Guo

Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems

Chendi Qian, Didier Chetelat, Christopher Morris

Analysis of Privacy Leakage in Federated Large Language Models

Minh Vu, Truc Nguyen, Tre’ Jeter, My T. Thai

Subsampling Error in Stochastic Gradient Langevin Diffusions

Kexin Jin, Chenguang Liu, Jonas Latz

Sequence Length Independent Norm-Based Generalization Bounds for Transformers

Jacob Trauger, Ambuj Tewari

Certified private data release for sparse Lipschitz functions

Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig

Importance Matching Lemma for Lossy Compression with Side Information

Buu Phan, Ashish Khisti, Christos Louizos

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions

Zulqarnain Q. Khan, Davin Hill, Aria Masoomi, Joshua T. Bone, Jennifer Dy

Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification

Marzi Heidari, Abdullah Alchihabi, Qing En, Yuhong Guo

Generalization Bounds for Label Noise Stochastic Gradient Descent

Jung Eun Huh, Patrick Rebeschini

Adaptive Discretization for Event PredicTion (ADEPT)

Jimmy Hickey, Ricardo Henao, Daniel Wojdyla, Michael Pencina, Matthew Engelhard

Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks

Soheila Molaei, Anshul Thakur, Ghazaleh Niknam, Andrew Soltan, Hadi Zare

Efficiently Computable Safety Bounds for Gaussian Processes in Active Learning

Jörn Tebbe, Christoph Zimmer, Ansgar Steland, Markus Lange-Hegermann, Fabian Mies

MMD-based Variable Importance for Distributional Random Forest

Clement Benard, Jeffrey Näf, Julie Josse