Efficient First Order Methods for Linear Composite Regularizers

Details Efficient First Order Methods for Linear Composite Regularizers Efficient First Order Methods for Linear Composite Regularizers

2011-04-07

arxiv.org/abs/1104.1436v1

Computer Science

Learning

19 pages, 8 figures

Scientific paper

A wide class of regularization problems in machine learning and statistics employ a regularization term which is obtained by composing a simple convex function \omega with a linear transformation. This setting includes Group Lasso methods, the Fused Lasso and other total variation methods, multi-task learning methods and many more. In this paper, we present a general approach for computing the proximity operator of this class of regularizers, under the assumption that the proximity operator of the function \omega is known in advance. Our approach builds on a recent line of research on optimal first order optimization methods and uses fixed point iterations for numerically computing the proximity operator. It is more general than current approaches and, as we show with numerical simulations, computationally more efficient than available first order methods which do not achieve the optimal rate. In particular, our method outperforms state of the art O(1/T) methods for overlapping Group Lasso and matches optimal O(1/T^2) methods for the Fused Lasso and tree structured Group Lasso.

Affiliated with

Also associated with

No associations

Rating

Efficient First Order Methods for Linear Composite Regularizers 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 First Order Methods for Linear Composite Regularizers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient First Order Methods for Linear Composite Regularizers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-353420