SOTAVerified

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

2017-09-05NeurIPS 2017Code Available1· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Reproductions