A generalized online mirror descent with applications to classification and regression
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 60547849X | ||
| 003 | CHVBK | ||
| 005 | 20210128100406.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150601xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s10994-014-5474-8 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s10994-014-5474-8 | ||
| 245 | 0 | 2 | |a A generalized online mirror descent with applications to classification and regression |h [Elektronische Daten] |c [Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi] |
| 520 | 3 | |a Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past few decades, some based on additive updates, like the Perceptron, and some on multiplicative updates, like Winnow. A unifying perspective on the design and the analysis of online algorithms is provided by online mirror descent, a general prediction strategy from which most first-order algorithms can be obtained as special cases. We generalize online mirror descent to time-varying regularizers with generic updates. Unlike standard mirror descent, our more general formulation also captures second order algorithms, algorithms for composite losses and algorithms for adaptive filtering. Moreover, we recover, and sometimes improve, known regret bounds as special cases of our analysis using specific regularizers. Finally, we show the power of our approach by deriving a new second order algorithm with a regret bound invariant with respect to arbitrary rescalings of individual features. | |
| 540 | |a The Author(s), 2014 | ||
| 700 | 1 | |a Orabona |D Francesco |u Yahoo Labs, 10036, New York, NY, USA |4 aut | |
| 700 | 1 | |a Crammer |D Koby |u Department of Electrical Engineering, The Technion, 32000, Haifa, Israel |4 aut | |
| 700 | 1 | |a Cesa-Bianchi |D Nicolò |u Department of Computer Science, Università degli Studi di Milano, 20135, Milan, Italy |4 aut | |
| 773 | 0 | |t Machine Learning |d Springer US; http://www.springer-ny.com |g 99/3(2015-06-01), 411-435 |x 0885-6125 |q 99:3<411 |1 2015 |2 99 |o 10994 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s10994-014-5474-8 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s10994-014-5474-8 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Orabona |D Francesco |u Yahoo Labs, 10036, New York, NY, USA |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Crammer |D Koby |u Department of Electrical Engineering, The Technion, 32000, Haifa, Israel |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Cesa-Bianchi |D Nicolò |u Department of Computer Science, Università degli Studi di Milano, 20135, Milan, Italy |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Machine Learning |d Springer US; http://www.springer-ny.com |g 99/3(2015-06-01), 411-435 |x 0885-6125 |q 99:3<411 |1 2015 |2 99 |o 10994 | ||