Online Learning: A Comprehensive Survey
Steven C. H. Hoi, Doyen Sahoo, Jing Lu, Peilin Zhao
TL;DR
This comprehensive survey analyzes online learning through problem formulation, theory, and a broad spectrum of algorithms. It highlights online convex optimization, regret bounds, and game-theoretic foundations as the backbone, then details supervised online methods (first- and second-order, kernel-based, and expert-advice frameworks) plus practical variants (cost-sensitive, transfer, multi-task, ranking, CF, and distributed settings). It further surveys online bandits, online active learning, semi-supervised and unsupervised online learning, and intersects with related areas like incremental and continual learning. The work identifies open challenges such as concept drift, scalability to big data streams, and the need for online deep learning, proposing directions toward robust, scalable, and versatile online learning systems with real-world impact.
Abstract
Online learning represents an important family of machine learning algorithms, in which a learner attempts to resolve an online prediction (or any type of decision-making) task by learning a model/hypothesis from a sequence of data instances one at a time. The goal of online learning is to ensure that the online learner would make a sequence of accurate predictions (or correct decisions) given the knowledge of correct answers to previous prediction or learning tasks and possibly additional information. This is in contrast to many traditional batch learning or offline machine learning algorithms that are often designed to train a model in batch from a given collection of training data instances. This survey aims to provide a comprehensive survey of the online machine learning literatures through a systematic review of basic ideas and key principles and a proper categorization of different algorithms and techniques. Generally speaking, according to the learning type and the forms of feedback information, the existing online learning works can be classified into three major categories: (i) supervised online learning where full feedback information is always available, (ii) online learning with limited feedback, and (iii) unsupervised online learning where there is no feedback available. Due to space limitation, the survey will be mainly focused on the first category, but also briefly cover some basics of the other two categories. Finally, we also discuss some open issues and attempt to shed light on potential future research directions in this field.