Metraipolis › archive › dc_c60e054ff468
Efficient Mass Matrix Estimation with Gaussian Cooling — arXiv:2610.04806
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.04806
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:33:41.411Z
- SHA-256 of the archived text
622c9b8caf320800a9d37bfa1cc3844449a2cafb98c3c33580b6ca7a48719ed5- Stable URL of this page
https://metraipolis.com/documento/dc_c60e054ff468
How to cite
Efficient Mass Matrix Estimation with Gaussian Cooling — arXiv:2610.04806 — arXiv (en), https://arxiv.org/abs/2610.04806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c60e054ff468 (Metraipolis archive dc_c60e054ff468, sha256 622c9b8caf320800a9d37bfa1cc3844449a2cafb98c3c33580b6ca7a48719ed5)
BibTeX
@misc{dcc60e054ff468,
title = {Efficient Mass Matrix Estimation with Gaussian Cooling — arXiv:2610.04806},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.04806},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c60e054ff468; sha256 622c9b8caf320800a9d37bfa1cc3844449a2cafb98c3c33580b6ca7a48719ed5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.04806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce an algorithm for efficiently preconditioning log-concave and log-smooth distributions that scales logarithmically with the condition number of the underlying distribution. Based on Gaussian cooling, our multistage method approximately samples from a sequence of well-conditioned distributions to construct a preconditioner for each subsequent stage of the cooling schedule. This method is motivated by existing practical approaches for mass matrix estimation in Markov chain Monte Carlo (MCMC), in which an effective preconditioner for the target distribution is estimated from samples produced during a warm-up period. However, our approach is conceptually distinct from existing approaches and moreover permits theoretical analysis. Our algorithmic framework is flexible, allowing essentially any log-concave sampling algorithm to act as the subroutine within each cooling stage. For instance, using first-order rejection sampling (FORS) as the sampler, the first-order query complexity of our method is $\tilde{O}(d^{4/3} \log \kappa)$ for a large class of log-concave and log-smooth distributions with condition number $\kappa$ and $\tilde{O}(d^{1/3} \log \kappa)$ for translation-invariant distributions. In the translation-invariant setting, we provide numerical experiments for the lattice $\phi^4$ model, a simple lattice field theory.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Computation (stat.CO) ; Probability (math.PR); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.04806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T08:24:13.982Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).