New Study Examines Regularization Versus Convolution in Kernel-Based Hypothesis Testing
A paper on arXiv analyzes the maximum mean discrepancy (MMD) test, a popular nonparametric test on general domains, comparing regularization and convolution approaches to its optimality.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-05 05:00 · arXiv stat.ML
Regularization vs. Convolution in Kernel-Based Hypothesis Testing