Online learning algorithms

Nicolò Cesa-Bianchi, Francesco Orabona

Research output: Contribution to journalArticlepeer-review

18 Scopus citations


Online learning is a framework for the design and analysis of algorithms that build predictive models by processing data one at the time. Besides being computationally efficient, online algorithms enjoy theoretical performance guarantees that do not rely on statistical assumptions on the data source. In this review, we describe some of the most important algorithmic ideas behind online learning and explain the main mathematical tools for their analysis. Our reference framework is online convex optimization, a sequential version of convex optimization within which most online algorithms are formulated. More specifically, we provide an in-depth description of online mirror descent and follow the regularized leader, two of the most fundamental algorithms in online learning. As the tuning of parameters is a typically difficult task in sequential data analysis, in the last part of the review we focus on coin-betting, an information-theoretic approach to the design of parameter-free online algorithms with good theoretical guarantees.
Original languageEnglish (US)
Pages (from-to)165-190
Number of pages26
JournalAnnual Review of Statistics and Its Application
StatePublished - Mar 7 2021
Externally publishedYes

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Online learning algorithms'. Together they form a unique fingerprint.

Cite this