YouTube Talk: AdaHessian Optimizer, With The Authors
I recently hosted a paper presentation of the AdaHessian optimizer from its authors
I recently hosted a presentation with the authors of the AdaHessian optimizer paper, Zhewei Yao and Amir Gholami and, to the fastai community.
AdaHessian is a promising new optimizer and one of the first second-order optimizers that is becoming practical to use. I've been working on a port of it to fastai which I hope to release shortly, I;ll post up here once I have it released. Until then, I hope you enjoy the presentation and Q&A afterwards!
(Click here of the embedded link below doesn't work)
Useful links
- Paper link
- AdaHessian Paper repo
- My Fastai Implementation, basic working version, mixed precision coming
- Fastai discussion
- @lessw2020, Best-Deep-Learning-Optimizers Code
- @davda54 pytorch implementation
@article{yao2020adahessian,
title={ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning},
author={Yao, Zhewei and Gholami, Amir and Shen, Sheng and Keutzer, Kurt and Mahoney, Michael W},
journal={arXiv preprint arXiv:2006.00719},
year={2020}
}
Thanks for Reading 😃
As always, I would love to hear if you have any comments, thoughts or criticisms, you can find me on Twitter at @mcgenergy