Metraipolis › archive › dc_754f80f4229b

A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps — arXiv:2608.15966

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15966
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:09.904Z
SHA-256 of the archived text
4086d64aa71ce67fd3223ec7dd9a736c29834410b5a9099f4b3188fa203bbc7b
Stable URL of this page
https://metraipolis.com/documento/dc_754f80f4229b

How to cite

A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps — arXiv:2608.15966 — arXiv (en), https://arxiv.org/abs/2608.15966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_754f80f4229b (Metraipolis archive dc_754f80f4229b, sha256 4086d64aa71ce67fd3223ec7dd9a736c29834410b5a9099f4b3188fa203bbc7b)
BibTeX
@misc{dc754f80f4229b,
  title = {A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps — arXiv:2608.15966},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15966},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_754f80f4229b; sha256 4086d64aa71ce67fd3223ec7dd9a736c29834410b5a9099f4b3188fa203bbc7b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study stochastic approximation of fixed points of a non-expansive operator $T$ when the oracle samples originate from a continuing Markovian trajectory. A direct block-minibatch implementation of Halpern iteration attains an expected last-iterate residual of order $O(\log N/N)$, but accrues a substantive complexity of $\tilde O(\epsilon^{-5})$ Markovian samples. We therefore introduce a variance-reduced Markovian PAGE-Halpern method whose refresh and same-state difference blocks are analyzed through the Poisson equation. In Hilbert spaces, the cocoercivity of $I-T$ results in an $O(\epsilon^{-3})$ sample complexity. Our main result extends this construction to a general finite-dimensional Banach space. A displacement-level Halpern bound replaces the Hilbert-space potential and yields $\tilde O(\epsilon^{-3})$ sample complexity. We also establish a high-probability guarantee with the same leading accuracy dependence by measuring the estimator in an auxiliary smooth norm.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.15966 — 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 2026-10-18T19:02:44.137Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).