Timezone: »

 
Poster
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
Will Grathwohl · Kuan-Chieh Wang · Joern-Henrik Jacobsen · David Duvenaud · Richard Zemel

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 06:00 PM -- 06:45 PM (PDT) @
in Poster Session 1 »

We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model’s log-density. We estimate the Stein discrepancy between the data density p(x) and the model density q(x) based on a vector function of the data. We parameterize this function with a neural network and fit its parameters to maximize this discrepancy. This yields a novel goodness-of-fit test which outperforms existing methods on high dimensional data. Furthermore, optimizing q(x) to minimize this discrepancy produces a novel method for training unnormalized models. This training method can fit large unnormalized models faster than existing approaches. The ability to both learn and compare models is a unique feature of the proposed method.

Keywords: Deep Generative Models · Generative Models · Unsupervised and Semi-supervised Learning · Probabilistic Inference - Models and Probabilistic Programming

Author Information

Will Grathwohl (University of Toronto)
Kuan-Chieh Wang (University of Toronto)
Joern-Henrik Jacobsen (Apple Inc.)
David Duvenaud (University of Toronto)
Richard Zemel (Vector Institute)

More from the Same Authors