← Back to papers
2020 ICML ICML 2020

SGD Learns One-Layer Networks in WGANs

Abstract

Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require solving a minmax optimization problem to global optimality, but are in practice successfully trained using stochastic gradient descent-ascent. In this paper, we show that, when the generator is a one-layer network, stochastic gradient descent-ascent converges to a global solution with polynomial time and sample complexity.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — one-layer network
🐣 Hot Topic Early Bird — global convergence
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Qi Lei , Jason Lee , Alex Dimakis , Constantinos Daskalakis

Topics

Machine Learning > Learning Types > Adversarial Learning Machine Learning > Optimization & Theory > Optimization Deep Learning > Models > Generative Models Deep Learning > Optimization & Theory > Optimization

Keywords

stochastic gradient descent global convergence generative adversarial network wasserstein gan minmax optimization one-layer network
Download PDF

Related papers

Correlation Clustering with Asymmetric Classification Errors 2020
Learning Portable Representations for High-Level Planning 2020
Proving the Lottery Ticket Hypothesis: Pruning is All You Need 2020
Minimax Pareto Fairness: A Multi Objective Perspective 2020
DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training 2020