Timezone: »

 
Poster
Conditional Generative Moment-Matching Networks
Yong Ren · Jun Zhu · Jialian Li · Yucen Luo

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #150 #None

Maximum mean discrepancy (MMD) has been successfully applied to learn deep generative models for characterizing a joint distribution of variables via kernel mean embedding. In this paper, we present conditional generative moment-matching networks (CGMMN), which learn a conditional distribution given some input variables based on a conditional maximum mean discrepancy (CMMD) criterion. The learning is performed by stochastic gradient descent with the gradient calculated by back-propagation. We evaluate CGMMN on a wide range of tasks, including predictive modeling, contextual generation, and Bayesian dark knowledge, which distills knowledge from a Bayesian model by learning a relatively small CGMMN student network. Our results demonstrate competitive performance in all the tasks.

Author Information

Yong Ren (Tsinghua University)
Jun Zhu (Tsinghua University)
Jialian Li (Tsinghua University)
Yucen Luo (Tsinghua University)

More from the Same Authors