Work

Symmetric Discrete Optimal Control and Deep Learning

Year: 2024

Type: preprint

Abstract: We analyze discrete optimal control problems and their connection with back propagation and deep learning. We consider in particular the symmetric representation of the discrete rigid body equations developed via optimal control analysis and optimal flows on adjoint orbits

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2404.06556

Authors: Bloch, Anthony M., Crouch, Peter E., Ratiu, Tudor S.

Institutions: University of Michigan, The University of Texas at Arlington, Shanghai Jiao Tong University

Language: English

Topic: Numerical methods for differential equations

Subfield: Numerical Analysis

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, National Centres of Competence in Research SwissMAP, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, National Natural Science Foundation of China, Air Force Office of Scientific Research

Awards: G138853884, Dynamics, Integrability, and Control of Mechanical and Physical Systems, 有限维动力系统可积的刻画及其动力学研究, G8010633306, G946381479

OpenAlex ID: W4394776170

Cites:

Cited by:

Related to: 10