Efficient Transductive Online Learning via Randomized Rounding
Machine Learning
2013-09-12 v4 Machine Learning
Abstract
Most traditional online learning algorithms are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, tailored for transductive settings, which combines "random playout" and randomized rounding of loss subgradients. As an application of our approach, we present the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question linking batch learning and transductive online learning
Cite
@article{arxiv.1106.2429,
title = {Efficient Transductive Online Learning via Randomized Rounding},
author = {Nicolò Cesa-Bianchi and Ohad Shamir},
journal= {arXiv preprint arXiv:1106.2429},
year = {2013}
}
Comments
To appear in a Festschrift in honor of V.N. Vapnik. Preliminary version presented in NIPS 2011