Rapid convergence of tempering chains to multimodal Gibbs measures

Abstract

We study the spectral gaps of parallel and simulated tempering chains targeting multimodal Gibbs measures. In particular, we consider chains constructed from Metropolis random walks that preserve the Gibbs distributions at a sequence of harmonically spaced temperatures. We prove that their spectral gaps admit polynomial lower bounds of order $11$ and $12$ in terms of the low target temperature. The analysis applies to a broad class of potentials, beyond mixture models, without requiring explicit structural information on the energy landscape. The main idea is to decompose the state space and construct a Lyapunov function based on a suitably perturbed potential, which allows us to establish lower bounds on the local spectral gaps.

Workflow Status

Review status: pending
Role: unreviewed
Read priority: later
Vote: Not set.
Saved: no
Collections: Not filed yet.
Next action: Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

BibTeX

@article{son2026rapid,
  title = {Rapid convergence of tempering chains to multimodal Gibbs measures},
  author = {Seungjae Son},
  year = {2026},
  abstract = {We study the spectral gaps of parallel and simulated tempering chains targeting multimodal Gibbs measures. In particular, we consider chains constructed from Metropolis random walks that preserve the Gibbs distributions at a sequence of harmonically spaced temperatures. We prove that their spectral gaps admit polynomial lower bounds of order \$11\$ and \$12\$ in terms of the low target temperature. The analysis applies to a broad class of potentials, beyond mixture models, without requiring explicit},
  url = {https://arxiv.org/abs/2604.04823},
  keywords = {math.PR, math.ST},
  eprint = {2604.04823},
  archiveprefix = {arXiv},
}

Metadata

{}