teaching
Lectures, schools, and student supervision in machine learning and particle physics.
I deliver machine learning teaching for students and researchers in high-energy physics, spanning interactive tutorials, summer schools, and laboratory instruction. I have also supervised 7 PhD students (6 defended; 1 ongoing) and DESY summer BSc/MSc students.
Lectures & schools
Terascale Statistics School 2026
Machine learning lecture series for students in high-energy physics.
- Materials: sjiggins/Terascale26-ML-Tutorials
DESY Summer School 2025
Lecture series on machine learning for the DESY summer student programme.
ATLAS Germany ML lecture series (2024–present)
Yearly interactive tutorials on machine learning for data analysis, aimed at BSc, MSc, PhD, and postdoctoral researchers on ATLAS within Germany (~100 participants).
Laboratory teaching — Universität Freiburg (2017–2021)
FP1 and FP2 laboratory teaching for BSc and MSc students. Designed and built three experiments; conducted entrance exams, graded reports, and provided scientific writing feedback.
PhD supervision
| Years | Student | Institution | Thesis |
|---|---|---|---|
| 2024–2027 | Stefan Katsarov | Humboldt-Universität zu Berlin | Ongoing |
| 2022–2024 | Lars Ferencz | Humboldt-Universität zu Berlin | Associated Higgs with top quarks, (H\to b\bar{b}), ATLAS |
| 2020–2022 | Adrian Jimenez | University of Valencia / IFIC | Dark matter, vector-like top, AI anomaly detection |
| 2020–2022 | Lubos Vozdecky | Queen Mary University | (H\to b\bar{b}) cross section; deep learning for background modelling |
| 2018–2022 | Thomas Charman | Queen Mary University | (H\to b\bar{b}) and (VH) production with ATLAS at 13 TeV |
| 2018–2019 | Carlos Viguel Vergel Infante | Iowa University | High-(p_T) (VH(bb)) with Center-of-Mass tagger |
| 2018–2021 | Simona Gargiulo | Universität Freiburg | (H\to b\bar{b}) observation/measurement; quasi-stable (b)-tagging |
Topics typically covered
- Supervised classification for analysis discrimination
- Likelihood-ratio estimation and reweighting of Monte Carlo
- Practical PyTorch workflows for HEP-style event data
- Connecting ML outputs to statistical inference