A Nondeterministic Minimization Algorithm

Abstract

The problem of minimizing a multivariate function is recurrent in many disciplines as Physics, Mathematics, Engineering and, of course, Computer Science. Both deterministic and nondeterministic algorithms have been devised to perform this task. It is common practice to use the nondeterministic algorithms when the function to be minimized is not smooth or depends on binary variables, as in the case of combinatorial optimization. In this paper we describe a simple nondeterministic algorithm which is based on the idea of adaptive noise, and that proved to be particularly effective in the minimization of a class of multivariate, continuous valued, smooth functions, associated with some recent extension of regularization theory by Poggio and Girosi (1990). Results obtained by using this method and a more traditional gradient descent technique are also compared.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1990
Accession Number
ADA231013

Entities

People

  • Bruno Caprile
  • Federico Girosi

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Computations
  • Contracts
  • Corporations
  • Data Sets
  • Department Of Defense
  • Information Processing
  • Information Systems
  • Iterations
  • Learning
  • Military Research
  • Numbers
  • Perturbations
  • Real Numbers
  • Standards

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Mathematical Modeling and Probability Theory.
  • Operations Research