Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics

Details Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics

2012-04-05

arxiv.org/abs/1204.1276v1

Statistics

Machine Learning

An extended and revised version of "Tight sample complexity of Large Margin Learning", NIPS 2010

Scientific paper

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of the data distribution, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the margin-adapted dimension of the data distribution. The upper bounds are universal, and the lower bounds hold for a rich family of sub-Gaussian distributions. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification.

Affiliated with

Also associated with

No associations

Rating

Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics 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 Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-213148