Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 47 min ago
PreprintarXiv licencearXiv

Rényi Tracking Bounds for Langevin Dynamics with Moving Targets

  • Yuchen Xin
  • Jingxin Zhan
  • Zhihua Zhang
Open at sourcePDFDOICite

Abstract

We study Langevin diffusion and Langevin Monte Carlo (LMC) when the target distribution changes over time. Under a log-Sobolev inequality (LSI), we derive non-asymptotic Rényi-divergence guarantees for tracking the current target. The framework covers continuous-time Langevin diffusion and its discretizations. We then apply the results to nonsmooth sampling based on successive Moreau envelopes. For this scheme, we give explicit choices of the smoothing parameters and step sizes, together with corresponding complexity bounds. To our knowledge, these are the first non-asymptotic Rényi-divergence tracking bounds for Langevin dynamics with discrete target updates.

Related

  1. Spectral Gap Bounds for Langevin Dynamics in Mixed Spherical Spin Glasses
    Masoud Badiei Khuzani
    arXivPreprintarXiv licenceFull textProbabilityarXiv
  2. Tempered Langevin diffusions with polynomial-tailed targets: explosions, moment thresholds and ergodicity
    Aleksandar Mijatović, Haokai Xie
    arXivPreprintarXiv licenceFull textProbabilityarXiv
  3. Wasserstein Bounds for Euler and Randomized Midpoint Langevin Sampling with Noisy Gradients
    Yifei Xiong, Vinayak Rao
    arXivPreprintCC BY 4.0Full textNumerical analysis & scientific computingStatisticsarXiv
  4. Equidistribution, multipliers, and moving targets in polynomial families
    Yûsuke Okuyama
    arXivPreprintarXiv licenceFull textAlgebra & number theoryAnalysis & PDEsarXiv
  5. Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA
    Gérard Ben Arous, Cédric Gerbelot, Vanessa Piccolo
    Probability Theory and Related FieldsPeer-reviewedLicence not statedFull text13 citedNumerical analysis & scientific computingOpenAlex

Cite

BibTeXRIS
BibTeX
@misc{xin2026rényi,
  title = {{Rényi Tracking Bounds for Langevin Dynamics with Moving Targets}},
  author = {Yuchen Xin and Jingxin Zhan and Zhihua Zhang},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.17577},
  eprint = {2609.17577},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17577},
}
RIS
TY  - UNPB
TI  - Rényi Tracking Bounds for Langevin Dynamics with Moving Targets
AU  - Yuchen Xin
AU  - Jingxin Zhan
AU  - Zhihua Zhang
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.17577
UR  - https://arxiv.org/abs/2609.17577
AB  - We study Langevin diffusion and Langevin Monte Carlo (LMC) when the target distribution changes over time. Under a log-Sobolev inequality (LSI), we derive non-asymptotic Rényi-divergence guarantees for tracking the current target. The framework covers continuous-time Langevin diffusion and its discretizations. We then apply the results to nonsmooth sampling based on successive Moreau envelopes. For this scheme, we give explicit choices of the smoothing parameters and step sizes, together with corresponding complexity bounds. To our knowledge, these are the first non-asymptotic Rényi-divergence tracking bounds for Langevin dynamics with discrete target updates.
ER  -