23/06/2021

DreamCoder: Bootstrapping Inductive Program Synthesis with Wake-Sleep Library Learning

Kevin Ellis, Catherine Wong, Maxwell Nye, Mathias Sablé-Meyer, Lucas Morales, Luke Hewitt, Luc Cary, Armando Solar-Lezama, Joshua B. Tenenbaum

Keywords: synthesis, neural, learning, refactoring

Abstract Paper Code Similar Papers

Abstract: We present a system for inductive program synthesis called DreamCoder, which inputs a corpus of synthesis problems each specified by one or a few examples, and automatically derives a library of program components and a neural search policy that can be used to efficiently solve other similar synthesis problems. The library and search policy bootstrap each other iteratively through a variant of "wake-sleep" approximate Bayesian learning. A new refactoring algorithm based on E-graph matching identifies common sub-components across synthesized programs, building a progressively deepening library of abstractions capturing the structure of the input domain. We evaluate on eight domains including classic program synthesis areas and AI tasks such as planning, inverse graphics, and equation discovery. We show that jointly learning the library and neural search policy leads to solving more problems, and solving them more quickly.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38956305
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at PLDI 2021 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
 5:18 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 10:26 
 0
 0
 0
 0
 12:15 
 0
 0
 0
 0
 5:24 
 0
 0
 0
 0
 4:29 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 9:35 
 0
 1
 1
 1
 3:24 
 0
 0
 0
 0
 8:19 
 1
 1
 0
 0
 3:28 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 8:40 
 0
 0
 0
 0
 7:54 
 0
 0
 0
 0
 15:32 
 0
 0
 0
 0
 12:48 
 0
 0
 0
 0
 13:05 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 0
 19:26 
 0
 0
 0
 0
 9:50 
 0
 0
 0
 0
 5:28 
 0
 0
 0
 0
 19:06 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 5:50 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 4:50 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 15:09 
 0
 0
 0
 0
 12:54 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 13:09 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 6:13 
 0
 0
 0
 0
 3:15