Metraipolis › archive › dc_7a73f76744eb

Stochastic Mirror Descent under Dependent Observations — arXiv:2610.41251

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41251
License (as archived)
CC0-1.0
Archived
2026-11-03T05:42:24.301Z
SHA-256 of the archived text
56cf193b7b91df9701d229eaac5469b9b558b64d2c2087c67f0956b524177db4
Stable URL of this page
https://metraipolis.com/documento/dc_7a73f76744eb

How to cite

Stochastic Mirror Descent under Dependent Observations — arXiv:2610.41251 — arXiv (en), https://arxiv.org/abs/2610.41251 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a73f76744eb (Metraipolis archive dc_7a73f76744eb, sha256 56cf193b7b91df9701d229eaac5469b9b558b64d2c2087c67f0956b524177db4)
BibTeX
@misc{dc7a73f76744eb,
  title = {Stochastic Mirror Descent under Dependent Observations — arXiv:2610.41251},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41251},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a73f76744eb; sha256 56cf193b7b91df9701d229eaac5469b9b558b64d2c2087c67f0956b524177db4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41251. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the non-asymptotic convergence of Stochastic Mirror Descent (SMD) algorithm when the noisy first-order oracle is driven by dependent observations. Departing from the classical i.i.d. assumption underlying most existing guarantees, we introduce a flexible ``forgetting" condition that accommodates geometrically or polynomially dependent sequences. Under this condition we derive explicit finite-sample accuracy bounds for the averaged SMD iterates, recovering the classical $O(1/T)$ and $O(1/\sqrt{T})$ rates in the large- and small-initial-error regimes. We instantiate the general framework on two applications: high-dimensional linear regression with dependent regressors and nonparametric estimation of the drift function of a functional autoregressive model.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.41251 — 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 2026-11-03T05:26:57.578Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).