howardheaton

Optimization Engineer

@TypalAcademy

Pinned Repositories

.github
OptWiki ReadMe
00
site
Code for OptWiki site
10
feasibility_fixed_point_networks
Feasibility algorithms (projection methods) with data-driven regularization
Language:Jupyter Notebook41
personal-site
Personal Website
00
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.
Language:Jupyter Notebook1 3 00
hj-prox
Language:Python8 4 03
WassersteinBasedProjections
Language:Jupyter Notebook10
jacobian_free_backprop
Implicit networks can be trained efficiently and simply by using Jacobian-free Backprop (JFB).
Language:Python34 5 05
proximal-projection-algorithm
Numerical examples for the paper "Proximal Projection Method for Stable Linearly Constrained Optimization".
Language:Jupyter Notebook3 0 00
xai-l2o
Optimization-based deep learning models can give explainability with output guarantees and certificates of trustworthiness.
Language:Python30

howardheaton's Repositories

howardheaton/feasibility_fixed_point_networks
Feasibility algorithms (projection methods) with data-driven regularization
Language:Jupyter Notebook41
howardheaton/personal-site
Personal Website
00