Wasserstein Generative Adversarial Networks

Martin Arjovsky; Soumith Chintala; Léon Bottou

2017 ICML ICML 2017

Wasserstein Generative Adversarial Networks

Abstract

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to different distances between distributions.

🧭 Keyword Pioneer — mode collapse

🐣 Hot Topic Early Bird — generative adversarial network

🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning

Authors

Martin Arjovsky , Soumith Chintala , Léon Bottou

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Adversarial Learning Machine Learning > Optimization & Theory > Optimization Deep Learning > Models > Generative Models Deep Learning > Learning Types > Adversarial Learning

Keywords

wasserstein distance distribution matching generative adversarial network mode collapse learning stability

Download PDF

Related papers

Bottleneck Conditional Density Estimation 2017

Constrained Policy Optimization 2017

Near-Optimal Design of Experiments via Regret Minimization 2017

Input Convex Neural Networks 2017

An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation 2017