Establishes measure-theoretic foundations for NML in regular non-smooth models and introduces the PDL-PPMH geometric MCMC sampler to compute stochastic complexity exactly.
For a PDL function ˆθand an integrable functionu(x), the formula states: Z X u(x)Jconsˆθ(x)dLN(x) = Z Θ Z ˆθ−1(θ′) u(x)dHN−k (x) dLK(θ′)
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.