Home
=======================================

.. raw:: html

    <a  href="https://github.com/sun-umn/NCVX"><img alt="_images/NCVX_logo.png" src="_images/NCVX_logo.png" style="width: 500px;" /></a><br> <br> 

NCVX Package
-------------

**NCVX (NonConVeX)** is a user-friendly and scalable python software package targeting general nonsmooth NCVX problems with nonsmooth constraints. **NCVX** is being developed by `GLOVEX <https://glovex.umn.edu/>`_ at the Department of Computer Science & Engineering, University of Minnesota, Twin Cities. 

The initial release of **NCVX** contains the solver **PyGRANSO**, a PyTorch-enabled port of `GRANSO <http://www.timmitchell.com/software/GRANSO/>`_ incorporating auto-differentiation, GPU acceleration, tensor input, and support for new QP solvers. As a highlight, **PyGRANSO** can solve general constrained deep learning problems, the first of its kind. 

.. raw:: html

    <a  href="https://github.com/sun-umn/PyGRANSO"><img alt="_images/PyGRANSO_logo_banner.png" src="_images/PyGRANSO_logo_banner.png" style="width: 600px;" /></a><br> <br> 


.. raw:: html

    <b>PyGRANSO: A PyTorch-enabled port of GRANSO with auto-differentiation</b> 



Get the Code
-------------

The source code of NCVX Package is available in the `NCVX Repository <https://github.com/sun-umn/NCVX>`_. 

The source code of PyGRANSO Solver is available in the `PyGRANSO Repository <https://github.com/sun-umn/PyGRANSO>`_. 

Update Logs
-----------------

**Version: 1.2.0 --- 2022-07-26**

   * Description: major fixes and improvements on LBFGS and Steering Strategy.

   * Fixed: Reducing memory usage for LBFGS. Now PyGRANSO can solve problem with ~15k parameters by using 14 GB memory; Update example: ortho RNN with max folding and orthonormal initialization; Allow high precision for QP solver; Allow part of optimization variables not showing up in objective (see SVM example); Fixed Code 12: terminated with steering failure; Fixed stationary failure: try different stationarity calculation, or set stationarity measure to be inf if encounter numerical issue

   * Added: Reorganize and add examples: perceptual/lp norm attack on ImageNet images. trace optimization with orthogonal constraints; unconstrained deep learning with LeNet5; logistic regression.

**Version: 1.1.0 --- 2022-02-20**

   * Description: major fixes and improvements.

   * Fixed: Avoid gradient accumulating in deep learning problem; Prevent memory leak problem when using torch tensor. See ex6 perceptual attack.

   * Changed: Update format of user-defined variables when using pygranso interface.

   * Packaging: Publish pygranso package on Pypi.

   * Added: ex 10 dictionary learning with torch.nn module; ex 11 orthogonal recurrent neural networks.

**Version: 1.0.0 --- 2021-12-27**

   * Description: initial public release of PyGRANSO.

   * Main features: auto-differentiation, GPU acceleration, tensor input, scalable QP solver, and zero dependency on proprietary packages. Multiple new examples added.


Contents
--------

.. toctree::
   :maxdepth: 1

   intro
   install
   settings/index
   examples/index
   highlight/index
   mistakes
   citation
   NCVX PyGRANSO Forum <https://groups.google.com/a/umn.edu/g/ncvx>

Acknowledgements
----------------------

We would like to thank `Frank E. Curtis <https://coral.ise.lehigh.edu/frankecurtis/>`_  and `Michael L. Overton <https://cs.nyu.edu/~overton/>`_ for their involvement in creating the BFGS-SQP algorithm that is implemented in the software package `GRANSO <http://www.timmitchell.com/software/GRANSO/>`_. This work was supported by UMII Seed Grant Program and NSF CMMI 2038403.

Contact
----------------------

For questions or bug reports, please either:
    * raise issues in the `PyGRANSO Repository <https://github.com/sun-umn/PyGRANSO>`_ or

    * send an email to our `NCVX PyGRANSO forum <https://groups.google.com/a/umn.edu/g/ncvx>`_: ncvx@umn.edu

Main authors:
        * Buyun Liang (byliang an_at_symbol seas a_dot_symbol upenn a_dot_symbol edu)
        * Tim Mitchell (tim an_at_symbol timmitchell a_dot_symbol com)
        * Ju Sun (jusun an_at_symbol umn a_dot_symbol edu)

Also, we are always looking for contributors and collaborators.


.. raw:: html

    <center><a href='https://clustrmaps.com/site/1buvz'  title='Visit tracker'><img src='//clustrmaps.com/map_v2.png?cl=ffffff&w=284&t=n&d=0dVX-NDd5VdZhjxgSpLRJ7NYKGM60A7_yy-QSSMfk4I'/></a></center><br><br>