CUED Publications database

Continuous relaxations for discrete Hamiltonian Monte Carlo

Zhang, Y and Sutton, C and Storkey, A and Ghahramani, Z (2012) Continuous relaxations for discrete Hamiltonian Monte Carlo. Advances in Neural Information Processing Systems, 4. pp. 3194-3202. ISSN 1049-5258

Full text not available from this repository.


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.

Item Type: Article
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:05
Last Modified: 22 May 2018 06:27