About Me
I am a PhD student in machine learning at the University of Tübingen and the International Max Planck Research School for Intelligent Systems (IMPRS-IS), supervised by Prof. Dr. Philipp Hennig. My research focuses on the development of efficient optimization algorithms for machine learning. In particular, I am interested in stochastic second-order optimizers. Prior to my PhD, I obtained a BSc and MSc in Computational Science and Engineering from Ulm University.
Publications
- Accelerating Generalized Linear Models by Trading off Computation for Uncertainty
Lukas Tatzel, Jonathan Wenger, Frank Schneider, Philipp Hennig
arXiv, 2024
[arXiv] [pdf] - Reparameterization invariance in approximate Bayesian inference
Hrittik Roy, Marco Miani, Carl Henrik Ek, Philipp Hennig, Marvin Pförtner, Lukas Tatzel, Søren Hauberg
arXiv, 2024
[arXiv] [pdf] - ViViT: Curvature Access Through The Generalized Gauss-Newton's Low-Rank Structure
Felix Dangel, Lukas Tatzel, Philipp Hennig
TMLR, 2023
[openreview] [pdf] [code] - Late-Phase Second-Order Training
Lukas Tatzel, Philipp Hennig, Frank Schneider
Neurips Workshop HITY, 2022
[openreview] [pdf]
Teaching & Supervision
I have been a teaching assistant for the Master courses "Data Literacy", "Probabilistic Machine Learning" and "Numerics of Machine Learning" at the University of Tübingen. As part of the course "Numerics of Machine Learning" (winter term of 2022/23), I gave a lecture on "Second-Order Optimization for Deep Learning". The entire lecture series is available on Youtube. I also supervised the Bachelor theses of Marco Wolfer, David Kern and Osane Hackel.