PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Efficient online learning via randomized rounding
Nicolò Cesa-Bianchi and Ohad Shamir
In: NIPS 2011(2012).


Most online algorithms used in machine learning today 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, which combines “random playout” and randomized rounding of loss subgradients. As an application of our approach, we provide 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.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:9194
Deposited By:Nicolò Cesa-Bianchi
Deposited On:21 February 2012