The paper proposes skew-reflected non-reversible Langevin dynamics and claims faster constrained sampling than projected Langevin Monte Carlo, with non-asymptotic bounds that are only partly justified.
A simple proof of the P oincar \'e inequality for a large class of probability measures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Non-Reversible Langevin Algorithms for Constrained Sampling
The paper proposes skew-reflected non-reversible Langevin dynamics and claims faster constrained sampling than projected Langevin Monte Carlo, with non-asymptotic bounds that are only partly justified.