iPULA replaces exact proximal steps with inexact approximations in unadjusted Langevin sampling and proves non-asymptotic convergence that holds up to a quantifiable bias from the inexactness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speeding Up Nonsmooth Bayesian MCMC Sampling via Inexact Proximal Unadjusted Langevin Algorithm
iPULA replaces exact proximal steps with inexact approximations in unadjusted Langevin sampling and proves non-asymptotic convergence that holds up to a quantifiable bias from the inexactness.