Adam-atan2 for Pytorch
Project description
Adam-atan2 - Pytorch
Implementation of the proposed Adam-atan2 optimizer in Pytorch
A multi-million dollar paper out of google deepmind proposes a small change to Adam update rule (using atan2
) to remove the epsilon altogether for numerical stability and scale invariance
Install
$ pip install adam-atan2-pytorch
Usage
# toy model
import torch
from torch import nn
model = nn.Linear(10, 1)
# import AdamAtan2 and instantiate with parameters
from adam_atan2_pytorch import AdamAtan2
opt = AdamAtan2(model.parameters(), lr = 1e-4)
# forward and backwards
for _ in range(100):
loss = model(torch.randn(10))
loss.backward()
# optimizer step
opt.step()
opt.zero_grad()
Todo
- foreach version
Citations
@inproceedings{Everett2024ScalingEA,
title = {Scaling Exponents Across Parameterizations and Optimizers},
author = {Katie Everett and Lechao Xiao and Mitchell Wortsman and Alex Alemi and Roman Novak and Peter J. Liu and Izzeddin Gur and Jascha Narain Sohl-Dickstein and Leslie Pack Kaelbling and Jaehoon Lee and Jeffrey Pennington},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:271051056}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
adam_atan2_pytorch-0.0.3.tar.gz
(417.2 kB
view hashes)
Built Distribution
Close
Hashes for adam_atan2_pytorch-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b38c1ed8face5f3acc6ea0a53657614061c4cc12a61211050627ac8e0c37d17f |
|
MD5 | 5e687acc8cfb28dfa126a9e3a1a277e4 |
|
BLAKE2b-256 | 157ad8225de2093ed9487a3e960d3fc15504bc72502d96509141dbb00d24faef |