26/08/2020

Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions

Grégoire Mialon, Julien Mairal, Alexandre d'Aspremont

Keywords:

Abstract Paper Similar Papers

Abstract: We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees. We derive loss functions that produce dual objectives with a sparse solution. We also show how to regularize convex losses to ensure such a dual sparsity-inducing property, and propose a general method to design screening tests for classification or regression based on ellipsoidal approximations of the optimal set. In addition to producing computational gains, our approach also allows us to compress a dataset into a subset of representative points.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AISTATS 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 10:46 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 13:41 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:47 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 17:01 
 0
 0
 0
 0
 16:09 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 1
 3:31 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 14:43 
 0
 0
 0
 1
 5:39 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 17:50 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 13:51 
 0
 0
 0
 0
 10:21 
 0
 0
 0
 0
 14:47 
 0
 0
 1
 1
 15:08 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 17:53 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 8:36 
 0
 0
 0
 0
 8:54 
 0
 0
 0
 0
 13:27 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 14:00 
 0
 0
 0
 0
 12:45 
 0
 0
 0
 0
 11:40