[Lisa_teatalk] Tea Talk 16 June Monday @13.00 AA3195 by Ian Goodfellow

Kyung Hyun Cho cho.k.hyun at gmail.com
Thu Jun 12 11:31:49 EDT 2014


Dear all,

Ian Goodfellow will guide us to the wonderful world of adversarial sampling
away from the hell of MCMC and iterative inference at the tea talk on
Monday (http://arxiv-web3.library.cornell.edu/abs/1406.2661, the paper
attached)

Hope to see many of you there!
- Cho

P.S. I am looking for volunteers who want to share their ideas or discuss
interesting papers at a tea talk! See
https://docs.google.com/spreadsheets/d/1_bbHxcm4r-rs63chcKfHuBsM3roHuud4CJJjCEqQfII/edit#gid=0

========

- Speaker: Ian Goodfellow
- Date and Time: 16 June 2014 @13.00
- Place: AA3195
- Abstract:

We propose a new framework for estimating generative models via an
adversarial process, in which we simultaneously train two models: a
generative model G that captures the data distribution, and a
discriminative model D that estimates the probability that a sample came
from the training data rather than G. The training procedure for G is to
maximize the probability of D making a mistake. This framework corresponds
to a minimax two-player game. In the space of arbitrary functions G and D,
a unique solution exists, with G recovering the training data distribution
and D equal to 1/2 everywhere. In the case where G and D are defined by
multilayer perceptrons, the entire system can be trained with
backpropagation. There is no need for any Markov chains or unrolled
approximate inference networks during either training or generation of
samples. Experiments demonstrate the potential of the framework through
qualitative and quantitative evaluation of the generated samples.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20140612/67c3a741/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 1406.2661v1.pdf
Type: application/pdf
Size: 530481 bytes
Desc: not available
Url : http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20140612/67c3a741/attachment-0001.pdf 


More information about the Lisa_teatalk mailing list