Iterative regularization for learning with convex loss functions
Name
15-115.pdf
Size
459.15 KB
Format
Adobe PDF
Checksum (MD5)
d208f3415679265602d066ac687e458c
Author(s)
Lin, Junhong
Zhou, Ding-Xuan
Rosasco, Lorenzo
Date Issued
May 2016
Journal
Journal of Machine Learning Research
Publisher
JMLR, Inc.
Citation
Lin, Junhong, Lorenzo Rosasaco, and Ding-Xuan Zhou. "Iterative Regularization for Learning with Convex Loss Functions." Journal of Machine Learning Research 17, 2016, pp. 1-38. © 2016 Junhong Lin, Lorenzo Rosasco and Ding-Xuan Zhou
Version
Final published version
Abstract
We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stopping an empirical iteration. We consider a nonparametric setting, in the framework of reproducing kernel Hilbert spaces, and prove consistency and finite sample bounds on the excess risk under general regularity conditions. Our study provides a new class of efficient regularized learning algorithms and gives insights on the interplay between statistics and optimization in machine learning.
MIT Department
McGovern Institute for Brain Research at MIT
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://www.jmlr.org/papers/volume17/15-115/15-115.pdf
