ALICE: Towards understanding adversarial learning for joint distribution matching

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

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 proceeding › Conference contribution

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 language	English (US)
Title of host publication	Advances in Neural Information Processing Systems
Publisher	Neural information processing systems foundation
Pages	5496-5504
Number of pages	9
State	Published - Jan 1 2017
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2021-02-09

Cite this

@inproceedings{900826cd23364fd8bb6e1e1c989d0385,

title = "ALICE: Towards understanding adversarial learning for joint distribution matching",

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.",

author = "Chunyuan Li and Hao Liu and Changyou Chen and Yunchen Pu and Liqun Chen and Ricardo Henao and Lawrence Carin",

note = "Generated from Scopus record by KAUST IRTS on 2021-02-09",

year = "2017",

month = jan,

day = "1",

language = "English (US)",

pages = "5496--5504",

booktitle = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - ALICE: Towards understanding adversarial learning for joint distribution matching

AU - Li, Chunyuan

AU - Liu, Hao

AU - Chen, Changyou

AU - Pu, Yunchen

AU - Chen, Liqun

AU - Henao, Ricardo

AU - Carin, Lawrence

N1 - Generated from Scopus record by KAUST IRTS on 2021-02-09

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85040657945&partnerID=8YFLogxK

M3 - Conference contribution

SP - 5496

EP - 5504

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -

ALICE: Towards understanding adversarial learning for joint distribution matching

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this