CP-MMD is a complexity-penalized criterion for kernel selection in MMD tests derived from concentration inequalities, allowing grid-free optimization over continuous kernel classes with Type-I error control and maximized power.
Generative models and model criticism via optimized maximum mean discrepancy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests
CP-MMD is a complexity-penalized criterion for kernel selection in MMD tests derived from concentration inequalities, allowing grid-free optimization over continuous kernel classes with Type-I error control and maximized power.