# Stabilizing Adversarial Nets With Prediction Methods

arXiv: https://arxiv.org/abs/1705.07364 · HTML: https://mlsanity.com/paper/1705.07364/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2017.

## Built on by (most cited first, 14 of 14)

- [Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization](https://mlsanity.com/paper/2105.15186/) (2021)
- [Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization](https://mlsanity.com/paper/2104.08708/) (2021)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities](https://mlsanity.com/paper/2204.09228/) (2022)
- [Boomerang: Local sampling on image manifolds using diffusion models](https://mlsanity.com/paper/2210.12100/) (2022)
- [On Convergence of Gradient Descent Ascent: A Tight Local Analysis](https://mlsanity.com/paper/2207.00957/) (2022)
- [DIPPA: An improved Method for Bilinear Saddle Point Problems](https://mlsanity.com/paper/2103.08270/) (2021)
- [Accelerated Proximal Alternating Gradient-Descent-Ascent for Nonconvex Minimax Machine Learning](https://mlsanity.com/paper/2112.11663/) (2021)
- [Adaptive Consensus Optimization Method for GANs](https://mlsanity.com/paper/2304.10317/) (2023)
- [Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets](https://mlsanity.com/paper/2302.00089/) (2023)
- [Adversarial Learned Fair Representations using Dampening and Stacking](https://mlsanity.com/paper/2203.08637/) (2022)
- [Competitive Gradient Optimization](https://mlsanity.com/paper/2205.14232/) (2022)
- [Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation](https://mlsanity.com/paper/2303.10452/) (2023)
- [On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities](https://mlsanity.com/paper/2608.06182/) (2026)

## Abstract (arXiv)

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not minimizers, of the loss function. The alternating stochastic gradient methods typically used for such problems do not reliably converge to saddle points, and when convergence does happen it is often highly sensitive to learning rates. We propose a simple modification of stochastic gradient descent that stabilizes adversarial networks. We show, both in theory and practice, that the proposed method reliably converges to saddle points, and is stable with a wider range of training parameters than a non-prediction method. This makes adversarial networks less likely to "collapse," and enables faster training with larger learning rates.