Back to Search
Start Over
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
- Publication Year :
- 2017
-
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.<br />Comment: NIPS 2017 (22 pages); short version (9 pages): http://people.duke.edu/~cl319/doc/papers/nips_2017_alice.pdf
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.1709.01215
- Document Type :
- Working Paper