# symplectic-gradient-adjustment

**Repository Path**: mirrors_deepmind/symplectic-gradient-adjustment

## Basic Information

- **Project Name**: symplectic-gradient-adjustment
- **Description**: A colab that implements the Symplectic Gradient Adjustment optimizer from "The mechanics of n-player differentiable games"
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-02-27
- **Last Updated**: 2025-10-06

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

This colab implements the [Symplectic Gradient Adjustment](http://proceedings.mlr.press/v80/balduzzi18a/balduzzi18a.pdf) (SGA) algorithm.
It then applies this optimizer to two different experiments:
* using a GAN to learn a 4 by 4 mixture of Gaussians;
* using a GAN to learn 75 dimensional Gaussian.

All experiments run in 5-10 minutes with a GPU, but can of course be much slower on CPU.

Use this link to run this notebook in colab:
https://colab.research.google.com/github/deepmind/symplectic-gradient-adjustment/blob/master/Symplectic_Gradient_Adjustment.ipynb