[Lisa_teatalk] Talk by Phil Bachman on Wednesday (18 March) at 13.30

Kyung Hyun Cho cho.k.hyun at gmail.com
Sat Mar 14 16:42:46 EDT 2015


Dear all,

Phil Bachman from our neighbouring McGill University will tell us about
training generative models, bringing in recent advances of variational
autoencoders and approximate Bayesian computation, in the view of policy
learning. See below for the detail.

Hope to see many of you there!
- Cho

===
Speaker: Phil Bachman (McGill University)
Date/Time: 18 March 2015 @13.30
Place: Z-200
Title: Learning policies for generating data
Abstract:
We develop an approach to training generative models that draws together
several current lines of research. Our approach is based on unrolling a
variational auto-encoder into a Markov chain and shaping the chain’s
trajectories using a technique inspired by recent work in Approximate
Bayesian computation. We show that the global minimizer of the resulting
objective is achieved when the generative model reproduces the target
distribution. To allow finer control over the behavior of our models, we
add a regularization term related to techniques used for shaping policy
search in reinforcement learning. We present empirical results on the MNIST
and TFD datasets which show that our approach exceeds the state-of-art
performance in quantitative measurements and from a qualitative point of
view.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20150314/52c54e3f/attachment.html 


More information about the Lisa_teatalk mailing list