| Title: |
Robust Kernel Hypothesis Testing under Data Corruption |
| Authors: |
Schrab, Antonin; Kim, Ilmun |
| Contributors: |
Gatsby Computational Neuroscience Unit; Department of Computer science University College of London UCL-CS; The Inria London Programme Inria-London; MOdel for Data Analysis and Learning MODAL; University College of London London UCL; Yonsei University |
| Publication Year: |
2025 |
| Collection: |
LillOA (Lille Open Archive - Université de Lille) |
| Description: |
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 corruption, and we prove their consistency in power under minimal conditions. This contributes to the practical deployment of hypothesis tests for real-world applications with potential adversarial attacks. For the two-sample and independence settings, we show that our kernel robust tests are minimax optimal, in the sense that they are guaranteed to be non-asymptotically powerful against alternatives uniformly separated from the null in the kernel MMD and HSIC metrics at some optimal rate (tight with matching lower bound). We point out that existing differentially private tests can be adapted to be robust to data corruption, and we demonstrate in experiments that our proposed tests achieve much higher power than these private tests. Finally, we provide publicly available implementations and empirically illustrate the practicality of our robust tests. |
| Document Type: |
conference object |
| File Description: |
application/octet-stream |
| Language: |
English |
| Relation: |
International Conference on Artificial Intelligence and Statistics (AISTATS) 2025; PMLR; http://hdl.handle.net/20.500.12210/126609 |
| Availability: |
https://hdl.handle.net/20.500.12210/126609 |
| Rights: |
info:eu-repo/semantics/openAccess |
| Accession Number: |
edsbas.86AEE2CD |
| Database: |
BASE |