Pinned Repositories
.github
OptWiki ReadMe
site
Code for OptWiki site
feasibility_fixed_point_networks
Feasibility algorithms (projection methods) with data-driven regularization
personal-site
Personal Website
fpo-dys
Operator splitting can be used to design easy-to-train models for predict-and-optimize tasks, which scale effortlessly to problems with thousands of variables.
hj-prox
WassersteinBasedProjections
jacobian_free_backprop
Implicit networks can be trained efficiently and simply by using Jacobian-free Backprop (JFB).
proximal-projection-algorithm
Numerical examples for the paper "Proximal Projection Method for Stable Linearly Constrained Optimization".
xai-l2o
Optimization-based deep learning models can give explainability with output guarantees and certificates of trustworthiness.
howardheaton's Repositories
howardheaton/feasibility_fixed_point_networks
Feasibility algorithms (projection methods) with data-driven regularization
howardheaton/personal-site
Personal Website