Computer Science – Learning
Scientific paper
2009-10-04
Computer Science
Learning
Scientific paper
There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge). This work describes and analyzes a systematic method for constructing such matrix-based, regularization methods. In particular, we focus on how the underlying statistical properties of a given problem can help us decide which regularization function is appropriate. Our methodology is based on the known duality fact: that a function is strongly convex with respect to some norm if and only if its conjugate function is strongly smooth with respect to the dual norm. This result has already been found to be a key component in deriving and analyzing several learning algorithms. We demonstrate the potential of this framework by deriving novel generalization and regret bounds for multi-task learning, multi-class learning, and kernel learning.
Kakade Sham M.
Shalev-Shwartz Shai
Tewari Ambuj
No associations
LandOfFree
Regularization Techniques for Learning with Matrices 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 Regularization Techniques for Learning with Matrices, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Regularization Techniques for Learning with Matrices will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-665472