Poster
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
Chunyuan Li · Hao Liu · Changyou Chen · Yuchen Pu · Liqun Chen · Ricardo Henao · Lawrence Carin
Pacific Ballroom #114
Keywords: [ Generative Models ] [ Adversarial Networks ] [ Unsupervised Learning ] [ Deep Learning ] [ Semi-Supervised Learning ]
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.
Live content is unavailable. Log in and register to view live content