`hessQuik`: Fast Hessian computation of composite functions

Python Jupyter Notebook Submitted 08 February 2022Published 25 April 2022

Editor: @jbytecode (all papers)
Reviewers: @GregaVrbancic (all reviews), @yhtang (all reviews)


Elizabeth Newman (0000-0002-6309-7706), Lars Ruthotto (0000-0003-0803-3299)


Newman et al., (2022). `hessQuik`: Fast Hessian computation of composite functions. Journal of Open Source Software, 7(72), 4171, https://doi.org/10.21105/joss.04171

@article{Newman2022, doi = {10.21105/joss.04171}, url = {https://doi.org/10.21105/joss.04171}, year = {2022}, publisher = {The Open Journal}, volume = {7}, number = {72}, pages = {4171}, author = {Elizabeth Newman and Lars Ruthotto}, title = {`hessQuik`: Fast Hessian computation of composite functions}, journal = {Journal of Open Source Software} }
Copy citation string · Copy BibTeX  

python pytorch deep neural networks input convex neural networks

Markdown badge



Authors of JOSS papers retain copyright.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Creative Commons License

Table of Contents
Public user content licensed CC BY 4.0 unless otherwise specified.
ISSN 2475-9066