REVIEW 3 cited by
Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry
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
Signed reviews
abstract
We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergence when $\nu$ satisfies log-Sobolev inequality (LSI) and $f$ has bounded second and third derivatives. This improves on the result for the Unadjusted Langevin Algorithm (ULA), and matches the fastest known rate for sampling under LSI (without Metropolis filter) with a better dependence on the LSI constant. We also prove convergence guarantees for PLA in R\'enyi divergence of order $q > 1$ when the biased limit satisfies either LSI or Poincar\'e inequality.
Forward citations
Cited by 3 Pith papers
-
On the query complexity of sampling from non-log-concave distributions
The paper characterizes the worst-case query complexity of sampling from smooth non-log-concave distributions as exponential in dimension, with matching lower and upper bounds.
-
ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
ScoreField couples contrast and current neural fields with a frozen score prior to regularize full-wave electromagnetic inverse scattering, reporting the best PSNR on simulated and Fresnel benchmarks.
-
Accelerated Information Gradient flow
The authors derive and analyze accelerated Nesterov-type gradient flows in probability space under four information metrics and use them to build faster mean-field MCMC sampling algorithms.
Discussion (0). Continue with ORCID to comment.