# Gradient clipping

> A commonly used mechanism to mitigate the exploding gradient problem by artificially limiting (clipping) the maximum value of gradients when using gradient descent) to train a model.[^1]

A commonly used mechanism to mitigate the [exploding gradient problem](https://wiki.g15e.com/pages/Exploding%20gradient%20problem.txt) by artificially limiting (clipping) the maximum value of gradients when using [gradient descent](https://wiki.g15e.com/pages/Gradient%20descent.txt)) to [train](https://wiki.g15e.com/pages/Training%20(machine%20learning.txt)) a [model](https://wiki.g15e.com/pages/Model%20(machine%20learning.txt)).[^1]

## Footnotes

[^1]: https://developers.google.com/machine-learning/glossary#gradient-clipping