Online Learning: A Comprehensive Survey

By Steven C. H. Hoi et al
Published on Oct. 18, 2024
Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Tasks and Applications
3. Taxonomy
4. Related Work and Further Reading
5. Problem Formulations and Related Theory
6. Statistical Learning Theory

Summary

Online learning represents a family of machine learning methods where a learner attempts to tackle predictive tasks by learning from data instances one by one. This survey provides a comprehensive overview of the online machine learning literature, categorizing works into online supervised learning, online learning with limited feedback, and online unsupervised learning. The survey also discusses the challenges and future research directions in the field. Online learning has become a promising technique for learning from continuous streams of data in various real-world applications. The article further delves into problem formulations, statistical learning theory, and theoretical foundations for online learning techniques.
×
This is where the content will go.