Metraipolis › archive › dc_e5ef3475596a
Smoothed Picard Hamiltonian Monte Carlo — arXiv:2609.06906
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06906
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:04.816Z
- SHA-256 of the archived text
f61d9983608139df64adeb4e413f752c02ce5b66cf9828916dbd9849bf5c4cb6- Stable URL of this page
https://metraipolis.com/documento/dc_e5ef3475596a
How to cite
Smoothed Picard Hamiltonian Monte Carlo — arXiv:2609.06906 — arXiv (en), https://arxiv.org/abs/2609.06906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5ef3475596a (Metraipolis archive dc_e5ef3475596a, sha256 f61d9983608139df64adeb4e413f752c02ce5b66cf9828916dbd9849bf5c4cb6)
BibTeX
@misc{dce5ef3475596a,
title = {Smoothed Picard Hamiltonian Monte Carlo — arXiv:2609.06906},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06906},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5ef3475596a; sha256 f61d9983608139df64adeb4e413f752c02ce5b66cf9828916dbd9849bf5c4cb6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a new low-accuracy sampler, called smoothed Picard Hamiltonian Monte Carlo, which combines Gaussian smoothing, Picard iteration, and higher-order discretization. For a log-concave target $\pi \propto \exp(-V)$ in dimension $d$ satisfying $0 \prec \alpha I \preceq \nabla^2 V \preceq \beta I$, with condition number $\kappa := \beta/\alpha$, smoothed Picard HMC returns a sample with $\sqrt \alpha\,W_2(\cdot,\pi) \le \varepsilon$ using $\widetilde O(\kappa^2 + \kappa^{7/6} d^{1/6}/\varepsilon^{1/3})$ gradient queries. We also prove stronger $W_q$ bounds, and then develop an algorithmic framework, the recursive warm start generator, to upgrade these $W_q$ bounds to stronger divergence guarantees. This produces a warm start for the proximal bouncy particle sampler, introduced in a companion work, leading to a high-accuracy log-concave sampler with complexity $\widetilde O((\kappa^{7/6} d^{1/6} + \kappa^{1/2} d^{1/4})\mathrm{polylog}(1/\varepsilon))$.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Statistics Theory (math.ST) ; Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG); Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.06906 — 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 2026-10-16T13:39:43.200Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).