Personal tools
You are here: Home Events Workshop: Dagmara Panas and Yichuan Zhang, Chair: Benigno Uria

Workshop: Dagmara Panas and Yichuan Zhang, Chair: Benigno Uria

— filed under:

  • ANC Workshop Talk
When Jun 18, 2013
from 11:00 AM to 12:00 PM
Where IF 4.31/4.33
Add event to calendar vCal

Dagmara Panas:  "A talk on how scientists become interested in obscure questions..."

In this talk I will show how side-questions and various issues coming up over the course of my PhD ended up stealing the limelight, such that I ended up trying to figure out what is the source of Kullback-Leibler divergence estimation bias.

Yichuan Zhang:

I'm going to talk about my NIPS paper last year on Continuous Relaxations for Discrete
Hamiltonian Monte Carlo. Continuous relaxations play an important role in discrete
optimization, but have not seen much use in approximate probabilistic inference. Here
we show that a general form of the Gaussian Integral Trick makes it possible to transform
a wide class of discrete variable undirected models into fully continuous systems. The
continuous representation allows the use of gradient-based Hamiltonian Monte Carlo for
inference, results in new ways of estimating normalization constants (partition functions),
and in general opens up a number of new avenues for inference in difficult discrete systems.
We demonstrate some of these continuous relaxation inference algorithms on a number of
illustrative problems.