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. Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 3732-3747, PMLR, 2020. [doi]

Abstract

Abstract is missing.