Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching

Authors

  • Jianwen Xie University of California, Los Angeles
  • Yang Lu University of California, Los Angeles
  • Ruiqi Gao University of California, Los Angeles
  • Ying Nian Wu University of California, Los Angeles

Keywords:

Deep generative models, Convolutional neural networks, Contrastive divergence, MCMC teaching

Abstract

This paper proposes a cooperative learning algorithm to train both the undirected energy-based model and the directed latent variable model jointly. The learning algorithm interweaves the maximum likelihood algorithms for learning the two models, and each iteration consists of the following two steps: (1) Modified contrastive divergence for energy-based model: The learning of the energy-based model is based on the contrastive divergence, but the finite-step MCMC sampling of the model is initialized from the synthesized examples generated by the latent variable model instead of being initialized from the observed examples. (2) MCMC teaching of the latent variable model: The learning of the latent variable model is based on how the MCMC in (1) changes the initial synthesized examples generated by the latent variable model, where the latent variables that generate the initial synthesized examples are known so that the learning is essentially supervised. Our experiments show that the cooperative learning algorithm can learn realistic models of images.

Downloads

Published

2018-04-29

How to Cite

Xie, J., Lu, Y., Gao, R., & Wu, Y. N. (2018). Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11834