Online Learning Algorithms
| العنوان: | Online Learning Algorithms |
|---|---|
| المؤلفون: | Francesco Orabona, Nicolò Cesa-Bianchi |
| المصدر: | Annual Review of Statistics and Its Application. 8:165-190 |
| بيانات النشر: | Annual Reviews, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Statistics and Probability, 021103 operations research, Regret minimization, Computer science, business.industry, Online learning, 0211 other engineering and technologies, 02 engineering and technology, Machine learning, computer.software_genre, 01 natural sciences, Regression, 010104 statistics & probability, Convex optimization, Artificial intelligence, 0101 mathematics, Statistics, Probability and Uncertainty, Online algorithm, business, computer, Analysis of algorithms |
| الوصف: | 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. |
| تدمد: | 2326-831X 2326-8298 |
| DOI: | 10.1146/annurev-statistics-040620-035329 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::baaaca78cac8fc0ecee8f7e4928ef04b https://doi.org/10.1146/annurev-statistics-040620-035329 |
| رقم الانضمام: | edsair.doi...........baaaca78cac8fc0ecee8f7e4928ef04b |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 2326831X 23268298 |
|---|---|
| DOI: | 10.1146/annurev-statistics-040620-035329 |