Rm-NML is introduced as a geometrically invariant extension of NML to Riemannian manifolds, with explicit computation shown for normal distributions on hyperbolic spaces.
The Jacobian matrix ∂ϕ ∂ψ (θ) is a matrix-valued function that is continuous with respect to θ, and the parameter space Θ is compact
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces
Rm-NML is introduced as a geometrically invariant extension of NML to Riemannian manifolds, with explicit computation shown for normal distributions on hyperbolic spaces.