mlsanityData to 14 Oct 2026

SGD Learns One-Layer Networks in WGANs

arXiv 1910.07030 ↗First posted 15 Oct 2019cs.LG stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2020: 1; 2021: 8; 2022: 6; 2023: 0; 2024: 1.

16 papers.

Sort:

By area:

  1. 2021Faster Single-loop Algorithms for Minimax Optimization without Strong Concavitycited by 49
  2. 2021The Complexity of Nonconvex-Strongly-Concave Minimax Optimizationcited by 45
  3. 2024Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimizationcited by 16
  4. 2021Understanding Overparameterization in Generative Adversarial Networkscited by 14
  5. 2021Reversible Gromov-Monge Sampler for Simulation-Based Inferencecited by 10
  6. 2022Learning (Very) Simple Generative Models Is Hardcited by 9
  7. 2021Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascentcited by 8
  8. 2021Generalization Error of GAN from the Discriminator's Perspectivecited by 8
  9. 2022Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimizationcited by 7
  10. 2022A Mathematical Framework for Learning Probability Distributionscited by 7
  11. 2022Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANscited by 6
  12. 2022Dissecting adaptive methods in GANscited by 3
4 more
  1. 2021WGAN with an Infinitely Wide Generator Has No Spurious Stationary Pointscited by 1
  2. 2021On the Optimization Landscape of Maximum Mean Discrepancycited by 1
  3. 2020Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instabilitycited by 0
  4. 2022On the Nash equilibrium of moment-matching GANs for stationary Gaussian processescited by 0