06/12/2020

Coresets via Bilevel Optimization for Continual Learning and Streaming

Zalán Borsos, Mojmir Mutny, Andreas Krause

Keywords:

Abstract Paper Similar Papers

Abstract: Coresets are small data summaries that are sufficient for model training. They can be maintained online, enabling efficient handling of large data streams under resource constraints. However, existing constructions are limited to simple models such as k-means and logistic regression. In this work, we propose a novel coreset construction via cardinality-constrained bilevel optimization. We show how our framework can efficiently generate coresets for deep neural networks, and demonstrate its empirical benefits in continual learning and in streaming settings.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at NeurIPS 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
 16:57 
 0
 0
 0
 0
 8:38 
 0
 0
 0
 0
 10:41 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 18:29 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 4:14 
 0
 0
 0
 0
 13:31 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 7:59 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 5:29 
 1
 1
 0
 1
 5:09 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 11:38 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 12:57 
 0
 0
 0
 0
 16:47 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 11:32 
 0
 0
 0
 0
 5:48 
 0
 0
 0
 0
 12:09 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 9:35 
 0
 0
 0
 0
 14:14 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 15:09 
 0
 0
 0
 0
 1:01