Efficient Online Learning via Randomized Rounding

Details Efficient Online Learning via Randomized Rounding Efficient Online Learning via Randomized Rounding

2011-06-13

arxiv.org/abs/1106.2429v3

Computer Science

Learning

Fixed some typos in the NIPS 2011 conference version

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Efficient Online Learning via Randomized Rounding does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Efficient Online Learning via Randomized Rounding, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient Online Learning via Randomized Rounding will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-429448