Follow
Lukas Tatzel
Lukas Tatzel
University of Tübingen, Tübingen AI Center
Verified email at uni-tuebingen.de
Title
Cited by
Cited by
Year
ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure
F Dangel, L Tatzel, P Hennig
arXiv preprint arXiv:2106.02624, 2021
132021
Reparameterization invariance in approximate Bayesian inference
H Roy, M Miani, CH Ek, P Hennig, M Pförtner, L Tatzel, S Hauberg
arXiv preprint arXiv:2406.03334, 2024
32024
Late-Phase Second-Order Training
L Tatzel, P Hennig, F Schneider
Has it Trained Yet? NeurIPS 2022 Workshop, 2022
32022
Accelerating Generalized Linear Models by Trading off Computation for Uncertainty
L Tatzel, J Wenger, F Schneider, P Hennig
arXiv preprint arXiv:2310.20285, 2023
22023
Debiasing mini-batch quadratics for applications in deep learning
L Tatzel, B Mucsányi, O Hackel, P Hennig
arXiv preprint arXiv:2410.14325, 2024
12024
Position: Curvature Matrices Should Be Democratized via Linear Operators
F Dangel, R Eschenhagen, W Ormaniec, A Fernandez, L Tatzel, ...
arXiv preprint arXiv:2501.19183, 2025
2025
Debiasing Mini-Batch Quadratics for Applications in Deep Learning
P Hennig, O Hackel, B Mucsányi, L Tatzel
arXiv, 2024
2024
Reparameterization invariance in approximate Bayesian inference
P Hennig, S Hauberg, L Tatzel, M Pförtner, CH Ek, M Miani, H Roy
arXiv, 2024
2024
Accelerating Generalized Linear Models by Trading off Computation for Uncertainty
P Hennig, F Schneider, J Wenger, L Tatzel
arXiv, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–9