Pith. sign in

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

arxiv 1911.01469 v1 pith:754HICQR submitted 2019-11-04 stat.ML cs.DScs.ITcs.LGmath.IT

classification stat.MLcs.DScs.ITcs.LGmath.IT
keywords algorithmconvergencelangevinunderdivergenceinequalityisoperimetryprove
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. On the query complexity of sampling from non-log-concave distributions

    cs.DS 2025-02 conditional novelty 8.0 of 10

    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.

  2. ScoreField: Neural Inverse Scattering with Score-Based Generative Priors

    eess.IV 2026-08 conditional novelty 6.0 of 10

    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.

  3. Accelerated Information Gradient flow

    math.OC 2019-09 conditional novelty 6.0 of 10

    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.

Pith tools