Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem
Stochastic Systems · 2020-06 · 10 (2) · 124-151
DOI: 10.1287/stsy.2019.0050 ↗Kurz gefasst
Fachartikel in der Zeitschrift Stochastic Systems, 2020-06. Verfasst von Justin Sirignano und 1 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 14 Literaturangaben.
Abstract (Originalsprache)
Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance. The SGDCT algorithm follows a (noisy) descent direction along a continuous stream of data. The parameter updates occur in continuous time and satisfy a stochastic differential equation. This paper analyzes the asymptotic convergence rate of the SGDCT algorithm by proving a central limit theorem for strongly convex objective functions and, under slightly stronger conditions, for nonconvex objective functions as well. An [Formula: see text] convergence rate is also proven for the algorithm in the strongly convex case. The mathematical analysis lies at the intersection of stochastic analysis and statistical learning.
Zitieren
APA
Sirignano, J., & Spiliopoulos, K. (2020). Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem. Stochastic Systems, 10(2), 124-151. https://doi.org/10.1287/stsy.2019.0050
Vancouver
Sirignano J, Spiliopoulos K. Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem. Stochastic Systems. 2020;10(2):124-151. doi:10.1287/stsy.2019.0050
BibTeX
@article{Sirignano2020,
author = {Sirignano, Justin and Spiliopoulos, Konstantinos},
title = {Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem},
journal = {Stochastic Systems},
year = {2020},
volume = {10},
number = {2},
pages = {124--151},
doi = {10.1287/stsy.2019.0050}
}
EUVIMED