Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Reinterpreting Importance-Weighted Autoencoders
Chris Cremer, Quaid Morris, David Duvenaud
Feb 17, 2017 (modified: Feb 27, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:The standard interpretation of importance-weighted autoencoders is that they maximize a tighter lower bound on the marginal likelihood. We give an alternate interpretation of this procedure: that it optimizes the standard variational lower bound, but using a more complex distribution. We formally derive this result, and visualize the implicit importance-weighted approximate posterior.
TL;DR:IWAE optimizes the standard variational lowerbound, but using a more complex variational distribution
Conflicts:cs.toronto.edu, harvard.edu, cam.ac.uk
Enter your feedback below and we'll get back to you as soon as possible.