Dissertation/Thesis Abstract

Two problems in applications of PDE
by Zhu, Kangping, Ph.D., New York University, 2014, 84; 3635320
Abstract (Summary)

This thesis contains two different parts. For part I, we develop a PDE perspective on a model problem from the machine learning literature. The problem involves ''prediction" via ''regret minimization". Our PDE approach identifies the optimal strategies and the associated outcomes in a scaling limit where the number of time steps tends to 1. While our PDE is very nonlinear, explicit solutions are available in many cases due to a surprising and convenient link to the linear heat equation.

For part II, We consider H–αgradient flow of the Modica-Mortola energy. The evolution law can be viewed as a nonlocal analogue of the Cahn-Hilliard equation for α > 0; the limit as α= 0 is (formally at least) the volume preserving Allen-Cahn flow. When α > ½ , we prove a time-averaged upper bound on the typical length scale, of order t < 1/( 1 +2α) We also argue that for α > ½ the true time scale of the evolution is the original time scale (and that the case α < ½ is different). Finally, we derive the sharp interface limit of the flow using heuristic arguments.

Indexing (document details)
Advisor: Kohn, Robert V.
Commitee:
School: New York University
Department: Mathematics
School Location: United States -- New York
Source: DAI-B 76/01(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Mathematics
Keywords: Machine learning, Modica-Mortola energy, Partial differential equations
Publication Number: 3635320
ISBN: 978-1-321-16308-7
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest