Metraipolis › archive › dc_df261a140cde

Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems — arXiv:2610.19322

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19322
License (as archived)
CC0-1.0
Archived
2026-10-15T20:01:10.011Z
SHA-256 of the archived text
0f8c2af334683759120160e20de5d5257a21f50c1dac8605b55796294e22477b
Stable URL of this page
https://metraipolis.com/documento/dc_df261a140cde

How to cite

Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems — arXiv:2610.19322 — arXiv (en), https://arxiv.org/abs/2610.19322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df261a140cde (Metraipolis archive dc_df261a140cde, sha256 0f8c2af334683759120160e20de5d5257a21f50c1dac8605b55796294e22477b)
BibTeX
@misc{dcdf261a140cde,
  title = {Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems — arXiv:2610.19322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df261a140cde; sha256 0f8c2af334683759120160e20de5d5257a21f50c1dac8605b55796294e22477b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Minimax optimization refers to a class of optimization problems with some variables to minimize and other variables to maximize. Biased stochastic gradient methods have shown practical success in solving minimax problems to either improve robustness, enhance communication efficiency, or decrease computational costs. These successes motivate a lot of theoretical works to study the convergence of biased stochastic gradient methods, while their generalization analysis remains untouched. In this paper, we present the first framework to study the stability and generalization of biased stochastic gradient methods for minimax problems. We establish a connection between stability and generalization for minimax problems by relaxing the existing bounded gradient assumption to a bounded second moment condition. We then introduce a generalized Lipschitz-type condition on bias and gradient estimators, and derive a general stability bound to clarify the connection among bias, gradient estimators, and stability. We apply our general analysis to Zeroth-order and Clipped stochastic gradient descent ascent (SGDA), and derive stability bounds that match those of SGDA under appropriate smoothing/clipping parameters. We combine stability and convergence analyses together, and derive optimal excess risk bounds of order $1/\sqrt{n}$, where $n$ is the sample size.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19322 — 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 2026-10-15T19:35:48.213Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).