Metraipolis › archive › dc_024d20013b96
Geometric Moment Contraction for Stochastic Nesterov Acceleration — arXiv:2609.31303
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31303
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:19:18.203Z
- SHA-256 of the archived text
9cea44542aa3c5198e360f904156999b24958cc52dbc9eb8ed9691fde1b6c8ac- Stable URL of this page
https://metraipolis.com/documento/dc_024d20013b96
How to cite
Geometric Moment Contraction for Stochastic Nesterov Acceleration — arXiv:2609.31303 — arXiv (en), https://arxiv.org/abs/2609.31303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_024d20013b96 (Metraipolis archive dc_024d20013b96, sha256 9cea44542aa3c5198e360f904156999b24958cc52dbc9eb8ed9691fde1b6c8ac)
BibTeX
@misc{dc024d20013b96,
title = {Geometric Moment Contraction for Stochastic Nesterov Acceleration — arXiv:2609.31303},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31303},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_024d20013b96; sha256 9cea44542aa3c5198e360f904156999b24958cc52dbc9eb8ed9691fde1b6c8ac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study geometric moment contraction (GMC) of the constant-parameter stochastic Nesterov recursion \[ Y_k=\Theta_k+\beta(\Theta_k-\Theta_{k-1}),\qquad \Theta_{k+1}=Y_k-\gamma G(Y_k,X_{k+1}). \] Under mean strong monotonicity and stochastic $L^p$ Lipschitz continuity, an explicit Perron comparison proves synchronous $L^p$ contraction when $\beta\gamma L_p<(1-\beta)(1-q_{\gamma,p})$. This direct criterion includes infinite-variance gradients for $1<p<2$, but its small-step regime requires $\beta<\mu/(\mu+L_p)$. A complementary power-Lyapunov argument establishes a positive, generally much smaller, step-size interval for every fixed $\beta<1$ and every $p>1$, using only a finite $p$th gradient moment. At $p=2$, a simpler explicit certificate gives \[ 0<\gamma<\frac{2\mu(1-\beta)^2}{L_2^2(1-\beta+2\beta^2)}. \] Its quadratic high-momentum scaling is a limitation of the chosen metric, not a sharp stability boundary. We quantify this loss, provide a general mean-only quadratic $S$-procedure, and exploit endpoint Lyapunov inequalities under stronger samplewise sector information. Verified endpoint certificates can be orders of magnitude less conservative than the explicit metric.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.31303 — 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 2026-10-08T01:43:06.812Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).