Felix Dangel

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 17

Top Topics

Starting Points

Optimization Method

Parameter Space

Top Venues

Publications

Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective. CoRR (2024)
Samarth Bhatia, Felix Dangel
Lowering PyTorch's Memory Consumption for Selective Differentiation. CoRR (2024)
Mohamed Elsayed, Homayoon Farrahi, Felix Dangel, A. Rupam Mahmood
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning. CoRR (2024)
Felix Dangel, Johannes Müller, Marius Zeinhofer
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks. CoRR (2024)
Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets. CoRR (2023)
Agustinus Kristiadi, Felix Dangel, Philipp Hennig
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. NeurIPS (2023)
Agustinus Kristiadi, Felix Dangel, Philipp Hennig
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization. CoRR (2023)
Jonathan Wenger, Felix Dangel, Agustinus Kristiadi
On the Disconnect Between Theory and Practice of Overparametrized Neural Networks. CoRR (2023)
Felix Dangel, Lukas Tatzel, Philipp Hennig
ViViT: Curvature Access Through The Generalized Gauss-Newton's Low-Rank Structure. Trans. Mach. Learn. Res. 2023 (2023)
Felix Dangel
Convolutions Through the Lens of Tensor Networks. CoRR (2023)
Frank Schneider, Felix Dangel, Philipp Hennig
Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks. NeurIPS (2021)
Frank Schneider, Felix Dangel, Philipp Hennig
Cockpit: A Practical Debugging Tool for Training Deep Neural Networks. CoRR (2021)
Felix Dangel, Lukas Tatzel, Philipp Hennig
ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure. CoRR (2021)
Felix Dangel, Stefan Harmeling, Philipp Hennig
Modular Block-diagonal Curvature Approximations for Feedforward Architectures. AISTATS (2020)
Felix Dangel, Frederik Kunstner, Philipp Hennig
BackPACK: Packing more into Backprop. ICLR (2020)
Felix Dangel, Philipp Hennig
A Modular Approach to Block-diagonal Hessian Approximations for Second-order Optimization Methods. CoRR (2019)
Felix Dangel, Frederik Kunstner, Philipp Hennig
BackPACK: Packing more into backprop. CoRR (2019)