Fast Learning Rate of lp-MKL and its Minimax Optimality

Details Fast Learning Rate of lp-MKL and its Minimax Optimality Fast Learning Rate of lp-MKL and its Minimax Optimality

2011-03-27

arxiv.org/abs/1103.5202v2

Statistics

Machine Learning

16 pages, submitted to COLT2011

Scientific paper

In this paper, we give a new sharp generalization bound of lp-MKL which is a generalized framework of multiple kernel learning (MKL) and imposes lp-mixed-norm regularization instead of l1-mixed-norm regularization. We utilize localization techniques to obtain the sharp learning rate. The bound is characterized by the decay rate of the eigenvalues of the associated kernels. A larger decay rate gives a faster convergence rate. Furthermore, we give the minimax learning rate on the ball characterized by lp-mixed-norm in the product space. Then we show that our derived learning rate of lp-MKL achieves the minimax optimal rate on the lp-mixed-norm ball.

Affiliated with

Also associated with

No associations

Rating

Fast Learning Rate of lp-MKL and its Minimax Optimality 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 Fast Learning Rate of lp-MKL and its Minimax Optimality, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast Learning Rate of lp-MKL and its Minimax Optimality will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-94777