Follow
Felix Dangel
Felix Dangel
Postdoc at the Vector Institute, Toronto
Verified email at vectorinstitute.ai - Homepage
Title
Cited by
Cited by
Year
Backpack: Packing more into backprop
F Dangel, F Kunstner, P Hennig
International Conference on Learning Representations (ICLR), 2019
1212019
Topological invariants in dissipative extensions of the Su-Schrieffer-Heeger model
F Dangel, M Wagner, H Cartarius, J Main, G Wunner
Physical Review A, 2018
992018
Numerical calculation of the complex berry phase in non-Hermitian systems
M Wagner, F Dangel, H Cartarius, J Main, G Wunner
Acta Polytechnica, 2017
252017
Modular block-diagonal curvature approximations for feedforward architectures
F Dangel, S Harmeling, P Hennig
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
21*2020
Cockpit: A practical debugging tool for the training of deep neural networks
F Schneider, F Dangel, P Hennig
Advances in Neural Information Processing Systems (NeurIPS), 2021
132021
ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure
F Dangel, L Tatzel, P Hennig
Transactions on Machine Learning Research (TMLR), 2022
122022
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
W Lin, F Dangel, R Eschenhagen, K Neklyudov, A Kristiadi, RE Turner, ...
International Conference on Machine Learning (ICML), 2024
7*2024
On the disconnect between theory and practice of overparametrized neural networks
J Wenger, F Dangel, A Kristiadi
arXiv preprint arXiv:2310.00137, 2023
52023
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
A Kristiadi, F Dangel, P Hennig
Advances in Neural Information Processing Systems (NeurIPS), 2023
52023
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
M Elsayed, H Farrahi, F Dangel, AR Mahmood
International Conference on Machine Learning (ICML), 2024
32024
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
F Dangel, J Müller, M Zeinhofer
Advances in Neural Information Processing Systems (NeurIPS), 2024
32024
Can we remove the square-root in adaptive gradient methods? a second-order perspective
W Lin, F Dangel, R Eschenhagen, J Bae, RE Turner, A Makhzani
International Conference on Machine Learning (ICML), 2024
32024
Backpropagation Beyond the Gradient
F Dangel
University of Tübingen, 2023
32023
Mikroskopische Beschreibung eines Einkoppelprozesses für PT-symmetrische Bose-Einstein-Kondensate
F Dangel
University of Stuttgart, 2015
22015
Bosonic many-body systems with topologically nontrivial phases subject to gain and loss
F Dangel
University of Stuttgart, 2017
12017
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
W Ormaniec, F Dangel, SP Singh
arXiv preprint arXiv:2410.10986, 2024
2024
Lowering PyTorch's Memory Consumption for Selective Differentiation
S Bhatia, F Dangel
International Conference on Machine Learning (ICML), 2nd Workshop on …, 2024
2024
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
F Dangel
Advances in Neural Information Processing Systems (NeurIPS), 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–18