Published May 28, 2025
| Version v1
Software
Open
From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
Authors/Creators
-
1.
Hebrew University of Jerusalem
-
2.
Forschungszentrum Jülich
- 3. Rheinisch Westfälische Technische Hochschule Aachen RWTH Aachen Fakultät für Mathematik Informatik und Naturwissenschaften
Description
Code for From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
This repository contains the code accompanying the paper:
Rubin, N., Fischer, K., Lindner, J., Dahmen, D., Seroussi, I., Ringel, Z., Krämer, M., Helias, M. From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning (arxiv 2502.03210).
For any questions, please contact Noa Rubin (noa.rubin@mail.huji.ac.il), Kirsten Fischer (ki.fischer@fz-juelich.de) or Javed Lindner (javed.lindner@rwth-aachen.de).
Files
directional_fl_create_figures.ipynb
Files
(4.8 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:c1172339a283b915507bcfc66d8ebac2
|
73.3 kB | Download |
|
md5:7444a6f679b316f51f90167fb49d21c2
|
4.7 MB | Preview Download |
|
md5:f0dd45b14494034a3fb321962d49e333
|
11.4 kB | Download |
|
md5:3a6c14ec3f825142ad36f4586370df6c
|
3.5 kB | Download |
|
md5:95d693ba3f7df54313e532c402f6ff04
|
1.5 kB | Download |
|
md5:e96d615d3daf46a0af27b15db567173b
|
15.5 kB | Download |
|
md5:656e4f9a535e3f7e7b16b26f5ff7f33e
|
14.8 kB | Download |
|
md5:dcdab871d90cc8007d6fa0296624f73c
|
5.8 kB | Download |
|
md5:11dfe349234df0f7ccd481fc5d4fc0e9
|
1.7 kB | Download |
|
md5:d1e28e049d2c054050517946af72b827
|
5.9 kB | Download |
Additional details
Related works
- Is supplement to
- Publication: 10.48550/arXiv.2502.03210 (DOI)
Software
- Programming language
- Python