ML-Optimizers-JAX
RAdam
Our great sponsors
ML-Optimizers-JAX | RAdam | |
---|---|---|
1 | 4 | |
40 | 2,520 | |
- | - | |
4.5 | 0.0 | |
almost 3 years ago | over 2 years ago | |
Python | Python | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ML-Optimizers-JAX
-
ML Optimizers from scratch using JAX
Github link (includes a link to a Kaggle notebook to run it directly) - shreyansh26/ML-Optimizers-JAX
RAdam
-
[D] Why does a sudden increase in accuracy at a specific epoch in these model
Code for https://arxiv.org/abs/1908.03265 found: https://github.com/LiyuanLucasLiu/RAdam
-
[D] How to pick a learning rate scheduler?
common practice is to include some type of annealing (cosine, linear, etc.), which makes intuitive sense. for adam/adamw, it's generally a good idea to include a warmup in the lr schedule, as the gradient distribution without the warmup can be distorted, leading to the optimizer being trapped in a bad local min. see this paper. there are also introduced in this paper and subsequent works (radam, ranger, and variants) that don't require a warmup stage to stabilize the gradients. i would say in general, if you're using adam/adamw, include a warmup and some annealing, either linear or cosine. if you're using radam/ranger/variants, you can skip the warmup. how many steps to use for warmup/annealing are probably problem specific, and require some hyperparam tuning to get optimimal results
- Why is my loss choppy?
What are some alternatives?
DemonRangerOptimizer - Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay
AdaBound - An optimizer that trains as fast as Adam and as good as SGD.
dm-haiku - JAX-based neural network library
pytorch_warmup - Learning Rate Warmup in PyTorch
trax - Trax — Deep Learning with Clear Code and Speed
pytorch-optimizer - torch-optimizer -- collection of optimizers for Pytorch
AdasOptimizer - ADAS is short for Adaptive Step Size, it's an optimizer that unlike other optimizers that just normalize the derivative, it fine-tunes the step size, truly making step size scheduling obsolete, achieving state-of-the-art training performance
dnn_from_scratch - A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).
Best-Deep-Learning-Optimizers - Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable
flaxOptimizers - A collection of optimizers, some arcane others well known, for Flax.
deepnet - Educational deep learning library in plain Numpy.