mlsanityData to 7 Oct 2026

Training GANs with Centripetal Acceleration

arXiv 1902.08949 ↗First posted 24 Feb 2019cs.LG stat.MLcited by 13

Not on the map. Why?

Abstract (arXiv)

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 6; 2023: 2; 2024: 0; 2025: 2.

13 papers.

Sort:

  1. 2022Accelerated Single-Call Methods for Constrained Min-Max Optimizationcited by 31
  2. 2021No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimizationcited by 20
  3. 2022Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalitiescited by 18
  4. 2022Generalized Optimistic Methods for Convex-Concave Saddle Point Problemscited by 15
  5. 2022Optimal Algorithms for Decentralized Stochastic Variational Inequalitiescited by 14
  6. 2023First Order Methods with Markovian Noise: from Acceleration to Variational Inequalitiescited by 14
  7. 2021Complex Momentum for Optimization in Gamescited by 11
  8. 2022Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalitiescited by 8
  9. 2023Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalitiescited by 7
  10. 2022On Scaled Methods for Saddle Point Problemscited by 3
  11. 2021Training Generative Adversarial Networks with Adaptive Composite Gradientcited by 1
  12. 2025Layer-wise Quantization for Quantized Optimistic Dual Averagingcited by 1
1 more
  1. 2025Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guaranteescited by 0