ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

Part of Advances in Neural Information Processing Systems 30 (NIPS 2017)

Bibtex »Metadata »Paper »Reviews »Supplemental »

Authors

Chunyuan Li, Hao Liu, Changyou Chen, Yuchen Pu, Liqun Chen, Ricardo Henao, Lawrence Carin

Abstract

<p>We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We unify a broad family of adversarial models as joint distribution matching problems. Our approach stabilizes learning of unsupervised bidirectional adversarial learning methods. Further, we introduce an extension for semi-supervised learning tasks. Theoretical results are validated in synthetic data and real-world applications.</p>