vizier
Gradient-Free-Optimizers
vizier | Gradient-Free-Optimizers | |
---|---|---|
5 | 11 | |
1,173 | 1,103 | |
0.7% | - | |
9.3 | 5.0 | |
1 day ago | about 1 month ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
vizier
- [N] Google Open Sources Vizier, Hyperparameter + Blackbox Optimization Service at Scale
- Is there any premade evolutionary algorithm selecting optimal NN architectures in TensorFlow ?
- Google just open sourced its Vizier optimisation suite
- Python-based research interface for blackbox and hyperparameter optimization
Gradient-Free-Optimizers
- Show HN: Gradient-Free-Optimizers supports constrained optimization in v1.3
- Gradient-Free-Optimizers version 1.2 released
-
Gradient-Free-Optimizers A collection of modern optimization methods in Python
I would be very disappointed if that were the case.. no, it looks like it’s set up to capture variance. The BO algo wraps an “Expected Improvement Optimizer”:
https://github.com/SimonBlanke/Gradient-Free-Optimizers/blob...
Which selects new points based on both the model’s mean estimate and its variance. See around line 58
-
Hacker News top posts: Feb 28, 2021
Gradient-Free-Optimizers A collection of modern optimization methods in Python\ (0 comments)
- SimonBlanke/Gradient-Free-Optimizers A collection of modern optimization methods in Python
- Gradient-Free-Optimizers: A collection of modern optimization methods in Python
- Optimize any Python function with modern algorithms in numerical search spaces
What are some alternatives?
mango - Parallel Hyperparameter Tuning in Python
Hyperactive - An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.
SpaceDrones - A simple learning environment with space drones for evolution-inspired optimization.
opytimizer - 🐦 Opytimizer is a Python library consisting of meta-heuristic optimization algorithms.
keras-tuner - A Hyperparameter Tuning Library for Keras
surrogate-models - A collection of surrogate models for sequence model based optimization techniques
tune - An abstraction layer for parameter tuning
pybobyqa - Python-based Derivative-Free Optimization with Bound Constraints
mlr3hyperband - Successive Halving and Hyperband in the mlr3 ecosystem
optimization-tutorial - Tutorials for the optimization techniques used in Gradient-Free-Optimizers and Hyperactive.
baybe - Bayesian Optimization and Design of Experiments
urh - Universal Radio Hacker: Investigate Wireless Protocols Like A Boss