Metraipolis › archive › dc_4d596e6f2e35

A Stochastic Riemannian Alternating Descent Ascent Method for Nonsmooth Composite Expectation Optimization on Riemannian Manifolds — arXiv:2609.04116

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04116
License (as archived)
CC0-1.0
Archived
2026-10-17T02:26:54.605Z
SHA-256 of the archived text
dd515361772a9b304622ad7e8ab17e42c58e6b76e184131ceb9eed49d3aad74d
Stable URL of this page
https://metraipolis.com/documento/dc_4d596e6f2e35

How to cite

A Stochastic Riemannian Alternating Descent Ascent Method for Nonsmooth Composite Expectation Optimization on Riemannian Manifolds — arXiv:2609.04116 — arXiv (en), https://arxiv.org/abs/2609.04116 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d596e6f2e35 (Metraipolis archive dc_4d596e6f2e35, sha256 dd515361772a9b304622ad7e8ab17e42c58e6b76e184131ceb9eed49d3aad74d)
BibTeX
@misc{dc4d596e6f2e35,
  title = {A Stochastic Riemannian Alternating Descent Ascent Method for Nonsmooth Composite Expectation Optimization on Riemannian Manifolds — arXiv:2609.04116},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04116},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d596e6f2e35; sha256 dd515361772a9b304622ad7e8ab17e42c58e6b76e184131ceb9eed49d3aad74d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04116. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we consider a class of Riemannian nonsmooth composite expectation optimization problems, which arises in various machine learning, signal processing, and statistics applications. Noting that these problems admit structured minimax reformulations, we propose an efficient algorithm, named stochastic Riemannian alternating descent ascent method with recursive momentum (StoRADA-RM), to tackle them. StoRADA-RM performs one or multiple Riemannian stochastic gradient descent steps and then a proximal gradient ascent step at each iteration. To compute the Riemannian stochastic gradient, we propose a vector transport-free recursive momentum estimator that requires only $O(1)$ stochastic gradient evaluations per iteration. We prove that StoRADA-RM returns an $\epsilon$-Riemannian-stochastic-stationary point of a given problem in the said class in $O(\epsilon^{-3})$ iterations while making $O(\epsilon^{-3})$ calls to a stochastic first-order oracle (SFO). Both the iteration complexity and SFO complexity bounds are the best known in the literature for the said class of problems. The latter even matches the optimal lower bound for smooth nonconvex optimization with stochastic first-order algorithms. We then present numerical results on sparse principal component analysis and coordinate-independent sparse estimation to demonstrate the superior performance of our proposed method.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-04 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.04116 — 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 2026-10-17T02:07:43.353Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).