ALICE: Towards understanding adversarial learning for joint distribution matching

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

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

70 Scopus citations

Abstract

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.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages5496-5504
Number of pages9
StatePublished - Jan 1 2017
Externally publishedYes

Fingerprint Dive into the research topics of 'ALICE: Towards understanding adversarial learning for joint distribution matching'. Together they form a unique fingerprint.

Cite this