Chris Kolb
About
I am a PhD student at the Chair of Statistical Learning and Data Science (SLDS) in affiliation with the Munich Center for Machine Learning (MCML) since 2021.
Before that, I obtained a Bachelor's degree (B.Sc.) in Economics from Goethe University Frankfurt and a joint Master's degree (M.Sc.) in Statistics from Humboldt University of Berlin, Technical University Berlin, Free University Berlin, and Charité Berlin.
My research focus is two-fold: Currently, I'm highly interested in exact differentiable optimization for non-smooth objectives using overparametrization, particularly in the context of sparsity in deep learning. My second area of research is the amalgamation of classical statistical models and machine learning concepts to create interpretable and well-founded, but highly flexible and scalable hybrid approaches.
Furthermore, I am part of the Data Science Group chaired by Prof. David Rügamer.
Contact
Institut für Statistik
Ludwig-Maximilians-Universität München
Ludwigstraße 33
D-80539 München
chris.kolb [at] stat.uni-muenchen.de
Research Interests
- Deep Neural Networks and Generalization
- Overparametrization
- (Structured) Sparsity and Optimization
- Non-convex Regularization
- Semi-Structured Regression Models
- Deep Distributional Regression
Awards
- Best paper at IWSM 2023
You Can Find me on
References
- Kook L, Kolb C, Schiele P, Dold D, Arpogaus M, Fritz C, Baumann P, Kopper P, Pielok T, Dorigatt E, Rügamer D (2024) How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression 40th Conference on Uncertainty in Artificial Intelligence (UAI),
pdf. - Rügamer D, Kolb C, Weber T, Kook L, Nagler T (2024) Generalizing Orthogonalization for Models with Non-linearities 41st International Conference on Machine Learning (ICML),
link|pdf. - Kolb C, Müller CL, Bischl B, Rügamer D (2023) Smoothing the Edges: A General Framework for Smooth Optimization in Sparse Regularization using Hadamard Overparametrization. arXiv preprint arXiv:2307.03571.
link|pdf. - Kolb C, Bischl B, Müller CL, Rügamer D (2023) Sparse Modality Regression. Proceedings of the 37th International Workshop on Statistical Modelling, IWSM 2023,
link|pdf. - Rügamer D, Kolb C, Klein N (2022) Semi-Structured Distributional Regression. The American Statistician.
link|pdf. - Rügamer D, Kolb C, Fritz C, Pfisterer F, Kopper P, Bischl B, Shen R, Bukas C, Sousa LB de Andrade e, Thalmeier D, Baumann P, Kook L, Klein N, Müller CL (2022) deepregression: a Flexible Neural Network Framework for Semi-Structured Deep Distributional Regression. Journal of Statistical Software.
link|pdf.