View The Document

Accession Number:

AD1197255

Title:

Extending Accelerated Optimization into the PDE Framework

Author(s):

Author Organization(s):

Report Date:

2021-09-23

Abstract:

The primary goal is to extend momentum based methods (Heavy Ball, and Nesterov) from the finite dimensional framework into the infinite dimensional framework of gradient based optimization over the manifolds of functions, curves, surfaces, diffeomorphisms, and other distributed unknowns. This includes developing 1) a theory of PDE methods for accelerated gradient optimization 2) formulation of the specific PDE equations for the application of this theory in several optimization contexts 3) numerical methods for solving accelerated PDE systems 4) theoretical analysis of convergence rates and performance gains 5) development of efficient implementations amenable to parallel computing.

Pages:

9

File Size:

0.16MB

Descriptors:

Identifiers:

SubjectCategory:

Distribution Statement:

Approved For Public Release

View The Document