Global minimizer of large scale stochastic rosenbrock function: canonical duality approach

  • Authors:
  • Chaojie Li;David Yanf Gao

  • Affiliations:
  • School of Science, Information Technology and Engineering, University of Ballarat, Mt Helen, VIC, Australia;School of Science, Information Technology and Engineering, University of Ballarat, Mt Helen, VIC, Australia

  • Venue:
  • ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part IV
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Canonical duality theory for solving the well-known benchmark test problem of stochastic Rosenbrock function is explored by two canonical transformations. Global optimality criterion is analytically obtained, which shows that the stochastic disturbance of these parameters could be eliminated by a proper canonical dual transformation. Numerical simulations illustrate the canonical duality theory is potentially powerful for solving this benchmark test problem and many other challenging problems in global optimization and complex network systems.