12/07/2020

Near-Tight Margin-Based Generalization Bounds for Support Vector Machines

Allan Grønlund, Lior Kamma, Kasper Green Larsen

Keywords: Learning Theory

Abstract Paper Similar Papers

Abstract: Support Vector Machines (SVMs) are among the most fundamental tools for binary classification. In its simplest formulation, an SVM produces a hyperplane separating two classes of data using the largest possible margin to the data. The focus on maximizing the margin has been well motivated through numerous generalization bounds. In this paper, we revisit and improve the classic generalization bounds in terms of margins. Furthermore, we complement our new generalization bound by a nearly matching lower bound, thus almost settling the generalization performance of SVMs in terms of margins.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICML 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
 14:25 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 12:19 
 0
 0
 1
 1
 15:08 
 0
 0
 0
 0
 6:19 
 0
 0
 0
 0
 13:06 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 1
 13:21 
 0
 0
 0
 0
 10:50 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 12:14 
 0
 0
 0
 0
 3:44 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 4:51 
 0
 0
 0
 0
 7:52 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 15:30 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 0
 8:57 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 11:10 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 15:09 
 0
 0
 0
 0
 12:37 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 13:27 
 0
 0
 0
 0
 23:06 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 4:07 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:20 
 0
 0
 0
 0
 2:50