Coding Bayesian Optimization (Bayes Opt) with BOTORCH – Python example for hyperparameter tuning
| Channel | Publish Date | Thumbnail & View Count | Download Video |
|---|---|---|---|
 | Publish Date not found |  0 Views |
Bayesian optimization is one of the most common optimization algorithms. While there are some black box packages to use it, they don't allow for many custom changes and aren't well suited to all issues. Facebook AI has released a library called Bitorch, which allows customization of all the different layers of Bayes Opt (from the GP model to the acquisition function). In this video, you'll get a high-level overview of how to code a Bayesian optimization from scratch and what to consider. Based on this knowledge, you can then dive deeper into the individual sub-components to improve your own algorithm. It's a Python-based library!
Theory for BayesOpt: https://www.youtube.com/watch?v=M-NTkxfd7-8
BOTORCH: https://botorch.org
Chapter links:
0:00 Introduction
0:35 Show test function
2:26 Generate first samples
7:05 One Bayes Opt iteration
17:56 Optimization loop
28:55 Off
——————————————– —- ———————–
Data Science to go: https://paretos.com
Please take the opportunity to connect and share this video with your friends and family if you find it helpful.
