Timezone: »

 
Poster
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Will Grathwohl · Kevin Swersky · Milad Hashemi · David Duvenaud · Chris Maddison

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual #None

We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a Metropolis-Hastings sampler. We show empirically that this approach outperforms generic samplers in a number of difficult settings including Ising models, Potts models, restricted Boltzmann machines, and factorial hidden Markov models. We also demonstrate our improved sampler for training deep energy-based models on high dimensional discrete image data. This approach outperforms variational auto-encoders and existing energy-based models. Finally, we give bounds showing that our approach is near-optimal in the class of samplers which propose local updates.

Author Information

Will Grathwohl (University of Toronto)
Kevin Swersky (Google Brain)
Milad Hashemi (Google)
David Duvenaud (University of Toronto)
Chris Maddison (University of Toronto)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors