Establishes measure-theoretic foundations for NML in regular non-smooth models and introduces the PDL-PPMH geometric MCMC sampler to compute stochastic complexity exactly.
One begins with the data-space integral and uses the classical coarea formula for Lipschitz maps to transform it into the nested parameter-space integral
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Normalized Maximum Likelihood for Regular Non-Smooth Models: Measure-Theoretic Foundations and Geometric Sampling
Establishes measure-theoretic foundations for NML in regular non-smooth models and introduces the PDL-PPMH geometric MCMC sampler to compute stochastic complexity exactly.