Markov Chain Gradient Descent in Hilbert Spaces

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Roy, Priyanka, Saminger-Platz, Susanne
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908709665374208
author Roy, Priyanka
Saminger-Platz, Susanne
author_facet Roy, Priyanka
Saminger-Platz, Susanne
contents In this paper, we study a Markov chain-based stochastic gradient algorithm in general Hilbert spaces, aiming at approximating the optimal solution of a quadratic loss function. We establish probabilistic upper bounds on its convergence. We further extend these results to an online regularized learning algorithm in reproducing kernel Hilbert spaces, where the samples are drawn along a Markov chain trajectory.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08361
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Markov Chain Gradient Descent in Hilbert Spaces
Roy, Priyanka
Saminger-Platz, Susanne
Machine Learning
Functional Analysis
60J20, 68T05, 68Q32, 62L20
In this paper, we study a Markov chain-based stochastic gradient algorithm in general Hilbert spaces, aiming at approximating the optimal solution of a quadratic loss function. We establish probabilistic upper bounds on its convergence. We further extend these results to an online regularized learning algorithm in reproducing kernel Hilbert spaces, where the samples are drawn along a Markov chain trajectory.
title Markov Chain Gradient Descent in Hilbert Spaces
topic Machine Learning
Functional Analysis
60J20, 68T05, 68Q32, 62L20
url https://arxiv.org/abs/2410.08361