`

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
in Tuesday Posters »

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.

Keywords: Deep Learning or Neural Networks · Kernel Methods
[ PDF] 

Author Information

Yong Ren (Tsinghua University)
Jun Zhu (Tsinghua University)
Jialian Li (Tsinghua University)
Yucen Luo (Max Planck Institute for Intelligence Systems)

More from the Same Authors