A Note on Continuous-Time Online Learning
Year: 2025
Author: Lexing Ying
Journal of Machine Learning, Vol. 4 (2025), Iss. 1 : pp. 1–10
Abstract
In online learning, the data is provided in sequential order, and the goal of the learner is to make online decisions to minimize overall regrets. This note is concerned with continuous-time models and algorithms for several online learning problems: online linear optimization, adversarial bandit, and adversarial linear bandit. For each problem, we extend the discrete-time algorithm to the continuous-time setting and provide a concise proof of the optimal regret bound.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/jml.240605
Journal of Machine Learning, Vol. 4 (2025), Iss. 1 : pp. 1–10
Published online: 2025-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 10
Keywords: Online learning Online optimization Adversarial bandits Adversarial linear bandits.
Author Details
Lexing Ying Email