Work

A Note on Continuous-Time Online Learning

Year: 2024

Type: article

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.

Source: Journal of Machine Learning

DOI: 10.4208/jml.240605

Author: Lexing Ying

Institution: Stanford University

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: bronze

Funder: National Science Foundation

Awards: New Algorithms for Markov Decision Processes and Reinforcement Learning, Deep Learning for Inverse Problems