Skip to content
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SmoothDiff.jl

Code Style: Runic Aqua JET

Julia reference implementation of SmoothDiff for the NeurIPS 2025 paper "Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations".

The full experiments can be found here: https://github.com/adrhill/smoothdiff-experiments/

Acknowledgements

Adrian Hill gratefully acknowledges funding from the German Federal Ministry of Education and Research under the grant BIFOLD26B.

About

Code for the NeurIPS 2025 paper "Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations"

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages