Adversarial Training Improves Joint Energy-Based Generative Modelling

Rostislav Korst, Arip Asadulaev

Abstract: We propose the novel framework for generative modelling using hybrid energy-based models. In our method we combine the interpretable input gradients of the robust classifier and Langevin Dynamics for sampling. Using the adversarial training we improve not only the training stability, but robustness and generative modelling of the joint energy-based models.