Overview
This page gathers the class material for the winter 2025 U.S. Particle Accelerator School course on Optimization and Machine Learning for Accelerators.
Agenda
Lecture slides
- Organization slides
- Optimization 1: Introduction and local methods slides
- Optimization 2: More advanced methods slides
- Bayesian optimization 1 slides
- Bayesian optimization 2 slides
- Modern neural networks slides
- Uncertainty quantification in machine Learning slides
- Unsupervised learning slides
- Reinforcement learning slides
- Practical deployment and MLOps slides
Labs
The lab exercises are in Jupyter notebook format, and can be downloaded from the following Github repository: github.com/uspas/optimization_and_ml
During this course, the notebooks will be run on Google Colab and saved in Google Drive.
-
The first time: to download all the notebooks to your Google Drive, please follow this link and execute the cells.
-
Subsequently: to update the notebooks (e.g., download the lab solutions and/or exam after they are posted online), please follow this link and execute the cells.
Slack
The course will use the Slack workspace uspasml2025.slack.com for related communication, discussions and questions.