Asymptotic relaxation enhancing flows are constructed to achieve arbitrarily fast convergence in Langevin sampling from Gibbs measures while preserving the invariant distribution.
Ergodicity and error estimate of laws for a random splitting Langevin Monte Carlo
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.PR 2verdicts
UNVERDICTED 2representative citing papers
Proves dimension-free long-time reverse transportation inequality for non-globally-dissipative Langevin dynamics with non-convex potentials controlling Rényi divergence.
citing papers explorer
-
Accelerating sampling via asymptotic relaxation enhancing flows
Asymptotic relaxation enhancing flows are constructed to achieve arbitrarily fast convergence in Langevin sampling from Gibbs measures while preserving the invariant distribution.
-
Long-time reverse transportation inequalities for non-globally-dissipative Langevin dynamics
Proves dimension-free long-time reverse transportation inequality for non-globally-dissipative Langevin dynamics with non-convex potentials controlling Rényi divergence.