Learning without Concentration
author: Shahar Mendelson,
Australian National University
published: July 15, 2014, recorded: June 2014, views: 4961
published: July 15, 2014, recorded: June 2014, views: 4961
Slides
Related content
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Description
We obtain sharp bounds on the convergence rate of Empirical Risk Minimization performed in a convex class and with respect to the squared loss, without any boundedness assumptions on class members or on the target.
Rather than resorting to a concentration-based argument, the method relies on a ‘small-ball’ assumption and thus holds for heavy-tailed sampling and heavy-tailed targets. Moreover, the resulting estimates scale correctly with the ‘noise level’ of the problem.
When applied to the classical, bounded scenario, the method always improves the known estimates.
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
Write your own review or comment: