Two generator game: Learning to sample via linear goodness-of-fit test

Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong Liu, Yu Li, Ling Shao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Learning the probability distribution of high-dimensional data is a challenging problem. To solve this problem, we formulate a deep energy adversarial network (DEAN), which casts the energy model learned from real data into an optimization of a goodness-of-fit (GOF) test statistic. DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution. We design a two-level alternative optimization procedure to train the explicit and implicit generative networks, such that the hyper-parameters can also be automatically learned. Experimental results show that DEAN achieves high quality generations compared to the state-of-the-art approaches.
Original languageEnglish (US)
Title of host publication33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019
PublisherNeural information processing systems foundation
StatePublished - Jan 1 2019

Fingerprint Dive into the research topics of 'Two generator game: Learning to sample via linear goodness-of-fit test'. Together they form a unique fingerprint.

Cite this