MASLA replaces the gradient in MALA with an element of a conservative subdifferential field, yielding a Metropolis-Hastings sampler that is reversible for locally Lipschitz, non-convex targets when the potential is twice differentiable almost everywhere.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Metropolis-adjusted Subdifferential Langevin Algorithm
MASLA replaces the gradient in MALA with an element of a conservative subdifferential field, yielding a Metropolis-Hastings sampler that is reversible for locally Lipschitz, non-convex targets when the potential is twice differentiable almost everywhere.