Pith. sign in

REVIEW 2 cited by

Sampling with Adaptive Variance for Multimodal Distributions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.15220 v1 pith:OMCINCCT submitted 2024-11-20 cs.LG cs.NAmath.NAstat.COstat.ML

Sampling with Adaptive Variance for Multimodal Distributions

classification cs.LG cs.NAmath.NAstat.COstat.ML
keywords dynamicsgibbssamplingadaptivedistributionspotentialclassconvergence
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose and analyze a class of adaptive sampling algorithms for multimodal distributions on a bounded domain, which share a structural resemblance to the classic overdamped Langevin dynamics. We first demonstrate that this class of linear dynamics with adaptive diffusion coefficients and vector fields can be interpreted and analyzed as weighted Wasserstein gradient flows of the Kullback--Leibler (KL) divergence between the current distribution and the target Gibbs distribution, which directly leads to the exponential convergence of both the KL and $\chi^2$ divergences, with rates depending on the weighted Wasserstein metric and the Gibbs potential. We then show that a derivative-free version of the dynamics can be used for sampling without gradient information of the Gibbs potential and that for Gibbs distributions with nonconvex potentials, this approach could achieve significantly faster convergence than the classical overdamped Langevin dynamics. A comparison of the mean transition times between local minima of a nonconvex potential further highlights the better efficiency of the derivative-free dynamics in sampling.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Gradient-free Riemannian Langevin Sampler

    cs.LG 2026-07 conditional novelty 6.0

    GRiLS is a gradient-free MCMC proposal derived via a Lamperti transform of Riemannian Langevin dynamics, using a Gaussian approximation of the target to enable mode-hopping without gradient evaluations.

  2. Sampling Using Hybrid Stochastic Dynamics

    math.NA 2026-06 unverdicted novelty 6.0

    Hybrid stochastic dynamics for Gibbs sampling with exponential convergence to equilibrium and reduced mean exit time in radially symmetric cases.