Skip to content

Simple and extensible hypergradient for PyTorch

License

Notifications You must be signed in to change notification settings

moskomule/hypergrad

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

hypergrad pytest

Simple and extensible hypergradient for PyTorch

Installation

First, install PyTorch appropriately. Then,

pip install hypergrad

Methods

Implicit hypergradient approximation (via approximated inverse Hessian-vector product)

Implementation of these methods can be found in hypergrad/approximate_ihvp.py

Citation

@inproceedings{hataya2023nystrom,
    author = {Ryuichiro Hataya and Makoto Yamada},
    title = {{Nystr\"om Method for Accurate and Scalable Implicit Differentiation}},
    booktitle = {AISTATS},
    year = {2023}
}