Stefan Kolek

kolek@math.lmu.de · Munich, Germany

Education

• 2021-2025 PhD Computer Science
  • Ludwig-Maximilians-Universität München, Germany
  • Title: Sparse Representation Methods for Explainable Image Classification
• 2018-2021 MS Mathematics
  • Technische Universität Berlin, Germany
• 2015-2018 BS Mathematics
  • Ludwig-Maximilians-Universität München, Germany

Open Source

• CartoonX: A wavelet-based post-hoc explanation method for image classifiers. CartoonX visualizes the piece-wise smooth relevant part of an image after optimizing a sparse mask in the wavelet domain of the image to minimize the distortion in the classifier's output.
• Query Dictionary Learning for V-IP: An optimization algorithm to train Variational Information Pursuit (V-IP), a recently introduced a recently introduced learning framework to construct classifiers that are interpretable by-design, with a learned query dictionary.

Publications

• Learning Interpretable Queries for Explainable Image Classification with Information Pursuit.
  • S. Kolek, A. Chattopadhyay, K. Chan, H. Andrade-Loarca, G. Kutyniok, R. Vidal. ICCV 2025.
• Beyond the Calibration Point: Mechanism Comparison in Differential Privacy.
  • G. Kaissis*, S. Kolek*, B. Balle, J. Hayes, D. Rückert. ICML 2024.
• Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning.
  • G. Kaissis, A. Ziller, S. Kolek, A. Riess, D. Rückert. NeurIPS 2023.
• Explaining Image Classifiers with Multiscale Directional Image Representation.
  • S. Kolek, R. Windesheim, H. Andrade-Loarca, G. Kutyniok, R. Levie. CVPR 2023.
• Cartoon Explanation of Image Classifiers.
  • S. Kolek, D. Nguyen, R. Levie, J. Bruna, G. Kutyniok. ECCV 2022 (Oral).

Personal Interests