Artificial Intelligence

    

Tooling on MATLAB for Online Convex Optimization

Authors: Philip Naveen

This manuscript is merely a formal documentation of the purpose and details surrounding the online convex optimization toolbox (OCOBox) for MATLAB. The purpose of this toolbox is to provide a collection of algorithms that work under stochastic situations where traditional algorithmic theory does not fare so well. The toolbox encompasses a wide range of methods including Bayesian persuasion, bandit optimization, Blackwell approachability, boosting, game theory, projection-free algorithms, and regularization. In the future, we plan to extend OCOBox to interactive machine learning algorithms and develop a more robust GUI.

Comments: 42 Pages.

Download: PDF

Submission history

[v1] 2024-06-11 21:32:40

Unique-IP document downloads: 287 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus