Training Deep Energy-Based Models with f-Divergence Minimization

03/06/2020 ∙ by Lantao Yu, et al. ∙ 14

Deep energy-based models (EBMs) are very flexible in distribution parametrization but computationally challenging because of the intractable partition function. They are typically trained via maximum likelihood, using contrastive divergence to approximate the gradient of the KL divergence between data and model distribution. While KL divergence has many desirable properties, other f-divergences have shown advantages in training implicit density generative models such as generative adversarial networks. In this paper, we propose a general variational framework termed f-EBM to train EBMs using any desired f-divergence. We introduce a corresponding optimization algorithm and prove its local convergence property with non-linear dynamical systems theory. Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.



There are no comments yet.


page 30

page 31

page 32

page 33

page 34

page 35

page 36

page 37

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.