Metraipolis › archive › dc_299b29bfdf5b

Stochastic Lie-Bracket Approximations for Zeroth-Order Optimization on Manifolds — arXiv:2609.38069

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38069
License (as archived)
CC0-1.0
Archived
2026-10-07T18:02:15.076Z
SHA-256 of the archived text
1ffa1dddfa515239dc8df391fd41479cf2cdd14b348c6010449a2a0b75ab4458
Stable URL of this page
https://metraipolis.com/documento/dc_299b29bfdf5b

How to cite

Stochastic Lie-Bracket Approximations for Zeroth-Order Optimization on Manifolds — arXiv:2609.38069 — arXiv (en), https://arxiv.org/abs/2609.38069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_299b29bfdf5b (Metraipolis archive dc_299b29bfdf5b, sha256 1ffa1dddfa515239dc8df391fd41479cf2cdd14b348c6010449a2a0b75ab4458)
BibTeX
@misc{dc299b29bfdf5b,
  title = {Stochastic Lie-Bracket Approximations for Zeroth-Order Optimization on Manifolds — arXiv:2609.38069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_299b29bfdf5b; sha256 1ffa1dddfa515239dc8df391fd41479cf2cdd14b348c6010449a2a0b75ab4458},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a continuous-time algorithm for zeroth-order global optimization of smooth functions on compact manifolds that synthesizes Riemannian gradient dynamics using only objective measurements, without evaluating gradients. The algorithm is formulated as an ordinary differential equation driven by piecewise-smooth McShane-type approximations of the Wiener process, with a geometric compensation term that depends only on the actuation frame and not on the objective function. Our main result establishes infinite-horizon practical probabilistic guarantees for fixed approximation parameters. To this end, we show that the algorithm's trajectories approximate, in the mean-square sense, a Riemannian Langevin diffusion whose unique invariant Gibbs measure concentrates on the set of global minimizers. We exploit this approximation to establish finite-horizon probabilistic convergence guarantees and directly analyze the algorithm's long-time behavior to obtain the infinite-horizon result.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-30 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.38069 — 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 2026-10-07T17:35:03.575Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).