flaxOptimizers
ML-Optimizers-JAX
flaxOptimizers | ML-Optimizers-JAX | |
---|---|---|
1 | 1 | |
28 | 40 | |
- | - | |
0.0 | 4.5 | |
over 2 years ago | almost 3 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.
flaxOptimizers
-
[P] Implementation of MADGRAD optimization algorithm for Tensorflow
For those who are interested, I have a Flax implementation of MADGRAD in flaxOptimizers (here). The optimizer solid and a refreshing departure from Adam-derived optimizers. One big caveat, however, is that you will need to tune your hyperparameters as they are likely to be orders of magnitude different from Adam's value.
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
What are some alternatives?
opytimizer - 🐦 Opytimizer is a Python library consisting of meta-heuristic optimization algorithms.
RAdam - On the Variance of the Adaptive Learning Rate and Beyond
DemonRangerOptimizer - Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay
dm-haiku - JAX-based neural network library
trax - Trax — Deep Learning with Clear Code and Speed
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).
yaglm - A python package for penalized generalized linear models that supports fitting and model selection for structured, adaptive and non-convex penalties.