Metraipolis › archive › dc_5ff7d4862cec

A sequential smoothing majorant stochastic approximation method for nonconvex nonconcave minimax problems — arXiv:2609.11171

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11171
License (as archived)
CC0-1.0
Archived
2026-10-16T06:01:00.285Z
SHA-256 of the archived text
cbe248ff614192e2b84056670a5f4a12ee1e80884865ebf053028aa2fcaa744e
Stable URL of this page
https://metraipolis.com/documento/dc_5ff7d4862cec

How to cite

A sequential smoothing majorant stochastic approximation method for nonconvex nonconcave minimax problems — arXiv:2609.11171 — arXiv (en), https://arxiv.org/abs/2609.11171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ff7d4862cec (Metraipolis archive dc_5ff7d4862cec, sha256 cbe248ff614192e2b84056670a5f4a12ee1e80884865ebf053028aa2fcaa744e)
BibTeX
@misc{dc5ff7d4862cec,
  title = {A sequential smoothing majorant stochastic approximation method for nonconvex nonconcave minimax problems — arXiv:2609.11171},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11171},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ff7d4862cec; sha256 cbe248ff614192e2b84056670a5f4a12ee1e80884865ebf053028aa2fcaa744e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a sequential smoothing majorant stochastic approximation (SMSA) method for nonconvex-nonconcave minimax optimization problems. To overcome the nonconcavity of the inner maximization problem, we introduce a new majorant stochastic approximation with an $O\left(\beta_N^2\right)$ accuracy bound, where $\beta_N$ is the sample coverage radius. The accuracy bound significantly improves upon the $O\left(\beta_N\right)$ approximation bound for the standard stochastic approximation. Moreover, we establish nonasymptotic bounds for both global optimal values and minimizer sets, and prove consistency for the Clarke stationary points, as $\beta_N \downarrow 0$ almost surely. We show that the generated sequence by the SMSA method is bounded, and that the returned point is an approximate Clarke stationary point of the majorant stochastic approximation models. Numerical experiments on a synthetic toy example and robust logistic regression on two UCI datasets demonstrate improved approximation fidelity and lower mean robust test losses relative to the standard sampled approximation.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-11 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.11171 — 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 2026-10-16T05:52:41.402Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).