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. |
Year | Venue | Field |
---|---|---|
2017 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017) | Joint probability distribution,Synthetic data,Artificial intelligence,Conditional entropy,Mathematics,Machine learning,Adversarial system |
DocType | Volume | ISSN |
Conference | 30 | 1049-5258 |
Citations | PageRank | References |
7 | 0.42 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunyuan Li | 1 | 467 | 33.86 |
Hao Liu | 2 | 7 | 0.76 |
Changyou Chen | 3 | 365 | 36.95 |
Yunchen Pu | 4 | 88 | 8.55 |
Liqun Chen | 5 | 28 | 4.77 |
Ricardo Henao | 6 | 286 | 23.85 |
Lawrence Carin | 7 | 137 | 11.38 |