ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

2017/09/05 by Chunyuan Li, Li, Chunyuan, Hao Liu +11 · 2 citations
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #Speech Recognition and Synthesis

paper · pdf · doi:10.48550/arxiv.1709.01215

openalex publication_date 2017/09/05 · openalex created_date 2017/09/15 · openalex updated_date 2026/07/28

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.

Cited by

• Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
• LensCraft: Your Professional Virtual Cinematographer

Related

• Distributional Adversarial Networks
• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
• Towards Practical Non-Adversarial Distribution Matching
• Robustness to Adversarial Perturbations in Learning from Incomplete Data
• Adversarial Distributional Training for Robust Deep Learning