English

High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm

Computation 2025-02-27 v3 Statistics Theory Machine Learning Statistics Theory

Abstract

In this work, we propose a first-order sampling method called the Metropolis-adjusted Preconditioned Langevin Algorithm for approximate sampling from a target distribution whose support is a proper convex subset of Rd\mathbb{R}^{d}. Our proposed method is the result of applying a Metropolis-Hastings filter to the Markov chain formed by a single step of the preconditioned Langevin algorithm with a metric G\mathscr{G}, and is motivated by the natural gradient descent algorithm for optimisation. We derive non-asymptotic upper bounds for the mixing time of this method for sampling from target distributions whose potentials are bounded relative to G\mathscr{G}, and for exponential distributions restricted to the support. Our analysis suggests that if G\mathscr{G} satisfies stronger notions of self-concordance introduced in Kook and Vempala (2024), then these mixing time upper bounds have a strictly better dependence on the dimension than when is merely self-concordant. We also provide numerical experiments that demonstrates the practicality of our proposed method. Our method is a high-accuracy sampler due to the polylogarithmic dependence on the error tolerance in our mixing time upper bounds.

Keywords

Cite

@article{arxiv.2412.18701,
  title  = {High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm},
  author = {Vishwak Srinivasan and Andre Wibisono and Ashia Wilson},
  journal= {arXiv preprint arXiv:2412.18701},
  year   = {2025}
}

Comments

55 pages, 5 figures, 2 tables. Shorter version without experiments accepted at ALT 2025. v3: fixes minor typographical errors

R2 v1 2026-06-28T20:48:27.625Z