Metraipolis › archive › dc_671eb6508ccb

Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems — arXiv:2611.07334

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07334
License (as archived)
CC0-1.0
Archived
2026-11-06T14:51:08.179Z
SHA-256 of the archived text
7e661795d2282329774bef091c45ac58c96fcbcd28bdfd5e64def748c25f2c35
Stable URL of this page
https://metraipolis.com/documento/dc_671eb6508ccb

How to cite

Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems — arXiv:2611.07334 — arXiv (en), https://arxiv.org/abs/2611.07334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_671eb6508ccb (Metraipolis archive dc_671eb6508ccb, sha256 7e661795d2282329774bef091c45ac58c96fcbcd28bdfd5e64def748c25f2c35)
BibTeX
@misc{dc671eb6508ccb,
  title = {Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems — arXiv:2611.07334},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07334},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_671eb6508ccb; sha256 7e661795d2282329774bef091c45ac58c96fcbcd28bdfd5e64def748c25f2c35},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Last-iterate convergence guarantees for stochastic gradient methods have attracted significant attention as practical implementations typically return the last iterate instead of an average of the iterates. In this paper, we study two approaches for analyzing the last-iterate convergence of proximal and projected stochastic gradient methods without bounded domain or bounded variance assumptions, where black-box variational inference serves as a running example. Under two related assumptions relaxing the bounded variance, we show near-optimal anytime rate $\widetilde{\mathcal{O}}(1/\sqrt{T})$ for the last iterate. Moreover, when the horizon $T$ is known, we remove the logarithmic factor and obtain the optimal order $\mathcal{O}(1/\sqrt{T})$, matching the order known under bounded variance or bounded domain assumptions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.07334 — 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 2026-11-06T14:21:42.657Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).