Computer Science – Learning
Scientific paper
2011-08-23
Computer Science
Learning
10 pages
Scientific paper
We consider the problems of ridge (L2-regularized) and lasso (L1-regularized) linear regression in a partial-information setting, in which the learner is allowed to observe only a fixed number of attributes of each example at training time. We present simple and efficient algorithms for both problems, that are optimal (up to logarithmic factors) in the sense that they require to observe the same number of attributes as do full-information algorithms. By that, we answer an open problem recently posed by Cesa-Bianchi et al. (2010), and show their lower bound to be tight.
Hazan Elad
Koren Tomer
No associations
LandOfFree
Optimal Algorithms for Ridge and Lasso Regression with Partially Observed Attributes 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 Optimal Algorithms for Ridge and Lasso Regression with Partially Observed Attributes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal Algorithms for Ridge and Lasso Regression with Partially Observed Attributes will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-67216