Skip to content
conftrace_

AISTATS

ML/AI Core
4,802 papers · 1997–2025

AISTATS (International Conference on Artificial Intelligence and Statistics) sits at the interface of machine learning, statistics, and their applications.

Papers per year

84
125
126
423
583
'5
'10
'15
'20
'25

Top authors

Andreas Krause 36 papers
Masashi Sugiyama 28 papers
Csaba Szepesvári 27 papers
Francis Bach 26 papers
Zoubin Ghahramani 25 papers
Lawrence Carin 25 papers
Mihaela van der Schaar 22 papers
Quanquan Gu 22 papers
Yu-Xiang Wang 21 papers
Aarti Singh 21 papers

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their counts at this venue are combined. How identity is handled.

Newest papers

A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks 2025
The Strong Product Model for Network Inference without Independence Assumptions 2025
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment 2025
Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations 2025
Task-Driven Discrete Representation Learning 2025
Clustering Context in Off-Policy Evaluation 2025
Mean-Field Microcanonical Gradient Descent 2025
Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants 2025
Training Neural Samplers with Reverse Diffusive KL Divergence 2025
An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications 2025
M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling 2025
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory 2025
Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy 2025
Strategic Conformal Prediction 2025
AlleNoise - large-scale text classification benchmark dataset with real-world label noise 2025
Certifiably Quantisation-Robust training and inference of Neural Networks 2025
Density Ratio-based Proxy Causal Learning Without Density Ratios 2025
DPFL: Decentralized Personalized Federated Learning 2025
Analyzing Generative Models by Manifold Entropic Metrics 2025
On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients 2025
All AISTATS 2025 papers →