Sivan Sabato, Nathan Srebro, Naftali Tishby. Tight Sample Complexity of Large-margin Learning
Submitted on: Aug 24, 2012, 19:19:12
Natural Sciences / Computer Science / Analysis of algorithms
Description: We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the gamma-adapted-dimension, which is a simple function of the spectrum of a distribution's covariance matrix, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the gamma-adapted-dimension of the source distribution. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification. The bounds hold for a rich family of sub-Gaussian distributions.
The Library of Congress (USA) reference page : http://lccn.loc.gov/cn2013300046.
To read the article posted on Intellectual Archive web site please click the link below.