Establishes measure-theoretic foundations for NML in regular non-smooth models and introduces the PDL-PPMH geometric MCMC sampler to compute stochastic complexity exactly.
By the linearity of the integral, we can combine them: Bias(bfN) =E[ bfN]−f(θ ′) = Z X H(x) JA(x) q(x)dx− Z X H(x) JK ˆθ(x) q(x)dx = Z X H(x) 1 JA(x) − 1 JK ˆθ(x) ! q(x)dx
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.