[Lisa_teatalk] Tea Talk this FRIDAY!

Aaron Courville aaron.courville at gmail.com
Tue Nov 29 20:35:54 EST 2011


hi gang,

This week we have two practice talks (well one practice talk and one
practice poster :-)) for the upcoming NIPS conference. Guillaume and Arnaud
will each have about 30 minutes to give us there best pitch.
Come with questions, comments and critiques.

When: Firday Dec. 2nd, 14h00
Where: TBA

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Speaker: Guillaume Desjardins
Title: On Tracking The Partition Function

Markov Random Fields (MRFs) have proven very powerful both as density
estimators and feature extractors for classification. However, their
use is often limited by an inability to estimate the partition
function $Z$. In this paper, we exploit the gradient descent training
procedure of restricted Boltzmann machines (a type of MRF) to {\bf
track} the log partition function during learning. Our method relies
on two distinct sources of information: (1) estimating the change
$\Delta Z$ incurred by each gradient update, (2) estimating the
difference in $Z$ over a small set of tempered distributions using
bridge sampling. The two sources of information are then combined
using an inference procedure similar to Kalman filtering.  Learning
MRFs through Tempered Stochastic Maximum Likelihood, we can estimate
$Z$ using no more temperatures than are required for learning.
Comparing to both exact values and estimates using annealed importance
sampling (AIS), we show on several datasets that our method is able to
accurately track the log partition function. In contrast to AIS, our
method provides this estimate at each time-step, at a computational
cost similar to that required for training alone.

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Speaker: Arnaud Bergeron
A Common GPU n-Dimensional Array for Python and C

Currently there are multiple incompatible array/matrix/n-dimensional
base object implementations for GPUs.  This hinders the sharing of GPU
code and causes duplicate development work. This paper proposes and
presents a first version of a common GPU n-dimensional array (tensor)
named GpuNdArray that works with both CUDA and OpenCL. It will be
usable from Python, C, and possibly other programming languages.

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++


Cheers,
Aaron

-- 
Aaron C. Courville
Département d’Informatique et
de recherche opérationnelle
Université de Montréal
email:Aaron.Courville at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20111129/cfa23933/attachment.html 


More information about the Lisa_teatalk mailing list