Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling

Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Richard S. Zemel

Abstract: 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 dis...