Felix Dangel
~Felix_Dangel1
12
论文总数
6.0
年均投稿
平均评分
接收情况7/12
会议分布
ICLR
6
NeurIPS
4
ICML
2
发表论文 (12 篇)
20257 篇
4
Collapsing Taylor Mode Automatic Differentiation
NeurIPS 2025Poster
4
Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
ICML 2025Spotlight
7
Fast Fractional Natural Gradient Descent using Learnable Spectral Factorizations
ICLR 2025Rejected
5
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemmanian Geometry Finds It
ICLR 2025Rejected
4
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
ICML 2025Spotlight
4
Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
NeurIPS 2025Poster
5
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
ICLR 2025Spotlight
20245 篇
3
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
NeurIPS 2024Poster
4
Convolutions Through the Lens of Tensor Networks
ICLR 2024Rejected
3
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
NeurIPS 2024Poster
4
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets
ICLR 2024Rejected
4
On the Disconnect Between Theory and Practice of Overparametrized Neural Networks
ICLR 2024Rejected