538 citations
- University College LondonGB40 papers
- Institut national de recherche en sciences et technologies du numériqueFR7 papers
- University of CambridgeGB7 papers
- University of LondonGB6 papers
- University of OxfordGB6 papers
- Gatsby Charitable FoundationGB5 papers
- Google DeepMind (United Kingdom)GB3 papers
- Max Planck Institute for Intelligent SystemsDE3 papers
- Princeton UniversityUS3 papers
- University of California, BerkeleyUS3 papers
- University of TorontoCA3 papers
- Yonsei UniversityKR3 papers
52 papers
Sampling on Discrete Spaces with Temporal Point Processes
Cameron A. Stewart, Maneesh Sahani
Temporal point processes offer a powerful framework for sampling from discrete distributions, yet they remain underutilized in existing literature. We show how to construct, for an…
Training Neural Networks at Any Scale
Thomas Pethick, Kimon Antonakopoulos, Antonio Silveti-Falls +2
This article reviews modern optimization methods for training neural networks with an emphasis on efficiency and scale. We present state-of-the-art optimization algorithms under a…
A Unified View of Optimal Kernel Hypothesis Testing
Antonin Schrab
This paper provides a unifying view of optimal kernel hypothesis testing across the MMD two-sample, HSIC independence, and KSD goodness-of-fit frameworks. Minimax optimal separatio…
Credal Two-Sample Tests of Epistemic Uncertainty
Siu Lun Chau, Antonin Schrab, Arthur Gretton +2
We introduce credal two-sample testing, a new hypothesis testing framework for comparing credal sets -- convex sets of probability measures where each element captures aleatoric un…
Robust Kernel Hypothesis Testing under Data Corruption
Antonin Schrab, Ilmun Kim
We propose a general method for constructing robust permutation tests under data corruption. The proposed tests effectively control the non-asymptotic type I error under data corru…
Practical Kernel Tests of Conditional Independence
Roman Pogodin, Antonin Schrab, Yazhe Li +2
We describe a data-efficient, kernel-based approach to statistical testing of conditional independence. A major challenge of conditional independence testing is to obtain the corre…