Metraipolis › archive › dc_f5865fc6c73f

An Inexact Riemannian Proximal Momentum Variance-Reduced Method: Complexity Bounds and KL Sequential Convergence — arXiv:2608.16355

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16355
License (as archived)
CC0-1.0
Archived
2026-10-18T20:19:05.289Z
SHA-256 of the archived text
c80325337e8f88ee5c947b0966c90bf696ba11c7a946370f36584d8af8541b40
Stable URL of this page
https://metraipolis.com/documento/dc_f5865fc6c73f

How to cite

An Inexact Riemannian Proximal Momentum Variance-Reduced Method: Complexity Bounds and KL Sequential Convergence — arXiv:2608.16355 — arXiv (en), https://arxiv.org/abs/2608.16355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5865fc6c73f (Metraipolis archive dc_f5865fc6c73f, sha256 c80325337e8f88ee5c947b0966c90bf696ba11c7a946370f36584d8af8541b40)
BibTeX
@misc{dcf5865fc6c73f,
  title = {An Inexact Riemannian Proximal Momentum Variance-Reduced Method: Complexity Bounds and KL Sequential Convergence — arXiv:2608.16355},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16355},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5865fc6c73f; sha256 c80325337e8f88ee5c947b0966c90bf696ba11c7a946370f36584d8af8541b40},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a unified analysis of inexact stochastic Riemannian proximal optimization for finite-sum nonsmooth composite problems over compact embedded submanifolds. The framework accommodates variance-reduced gradient estimators, projected momentum, and inexact tangent-space proximal solves under a single conditional error-dissipation condition, verified for projection-based SVRG, SARAH/SPIDER, SAGA, and SAG. A computable Fenchel-dual residual criterion, with tolerance prescribed before sampling and inner iterations, enables explicit control of the inner work. We establish conditional expected descent, subsequential stationarity, and an \(O(\epsilon^{-2})\) outer complexity. With SARAH/SPIDER and accumulative regularization, iRPMVR attains \(O(n+\sqrt n\,\epsilon^{-2})\) component-gradient and \(O(\epsilon^{-3})\) proximal-operator complexities. We further develop an abstract KL principle for conditional expected descent with memory and summable tails using only the ordinary pointwise KL property. A counterexample shows that a power-type expected-KL implication used in earlier stochastic analyses can fail. The principle yields almost-sure finite length, whole-sequence convergence, and deterministic KL rates.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-18 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.16355 — 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 2026-10-18T19:45:07.852Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).