chameleonline
This webpage overviews events related to Computational and mAthematical MEthods in machine LEarning, Optimization and iNference (ChAMELEON) — a lecture and a summer school I have developed over the last couple of years.
Summer School 2025
This one week summer school introduced participants to mathematical techniques at the intersection of machine learning, inverse problems, and statistical inference, with an emphasis on numerical aspects. Mornings included lectures that provide a foundational understanding of the field. Participants learned about state-of-the-art approaches for solving both deterministic and statistical inverse problems of varying complexity. In the afternoons, participants engaged in hands-on assignments to gain practical experience. They learned how to execute code on a modern high-performance computing architecture.
The summer school also featured research talks by leading scientist in the field. Participants had also the oportunity to present their research results during a poster session.
A tentative schedule for the summer school is included below.
Code snippets for the problems discussed in this class will be posted on GitHub: https://github.com/andreasmang/chameleon.
Schedule
| Time | Monday | Tuesday | Wednesday | Thursday | Friday |
|---|---|---|---|---|---|
| 0900 - 1030 | Lecture 1 | Lecture 3 | Lecture 5 | Lecture 7 | Talk |
| 1030 - 1100 | Breakout | Breakout | Breakout | Breakout | Breakout |
| 1100 - 1230 | Lecture 2 | Lecture 4 | Lecture 6 | Lecture 8 | Talk |
| 1230 - 1300 | Q&A | Q&A | Q&A | Q&A | |
| 1300 - 1430 | Lunch | Lunch | Lunch | Lunch | |
| 1430 - 1700 | Independent Work | Independent Work | Independent Work | Independent |
Date and Location
The summer school took place at the University of Houston in CBB 124, August 11 to August 15, 2025, 9 AM to 5 PM.
Lectures
The summer school included eight lectures. These lectures covered the following material:
- Introduction to Inverse Problems
- Spectral Operator Theory in Inverse Problems
- Convex Optimization
- Convex Non-Smooth Optimization
- Optimization in Machine Learning
- Inverse Problems Governed by Dynamical Systems
- Numerical Methods for Machine Learning
Invited Research Talks
The summer school featured two virtual talks from Dr. Georg Stadler (NYU) and Dr. Arvind Saibaba (NC State) on Friday.
Participants
Over 40 participants attended the first installment of this summer school. They discussed the presented material, worked on project assignments related to the material covered during the lectures, and participated in a poster presentation. The participants are listed on the following webpage.
Support
The summer school is financially supported by NSF under the award DMS-2145845 and by the Research Computing Data Core at the University of Houston.
