Hi, I'm Stefan, welcome to my personal website! Currently, I'm pursuing a Computer Science Ph.D. at Ludwig-Maximilians-University Munich. My research focuses on Explainable AI and Differentially Private Machine Learning. A common theme in my PhD research is applying ideas from information theory and sparse representation theory to Explainable AI. Currently, I am working on deep learning based models that are explainable by design and differentially private deep learning.
S. Kolek, A. Chattopadhyay, K. Chan, H. Andrade-Loarca, G. Kutyniok, R. Vidal. Learning Interpretable Queries for Explainable Image Classification with
Information Pursuit. Preprint Dec 2023
PDF
G. Kaissis, A. Ziller, S. Kolek, A. Riess, D. Rückert. Optimal privacy guarantees for a relaxed threat model:
Addressing sub-optimal adversaries in differentially
private machine learning. NeurIPS 2023
PDF
S. Kolek, R. Windesheim, H. Andrade-Loarca, G. Kutyniok, R. Levie. Explaining Image
Classifiers with Multiscal Directional Image Representation. CVPR 2023
PDF | Code
S. Kolek, D. Nguyen, R. Levie, J. Bruna, G. Kutyniok. Cartoon Explanations of Image
Classifiers. ECCV 2022 (Oral)
PDF |
Code
Reach out and say hi if you are interested in my research or working together: kolek@math.lmu.de