Bayesian Optimization Algorithm: From Single Level to Hierarchy
Pelikan, Martin
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/81610
Description
Title
Bayesian Optimization Algorithm: From Single Level to Hierarchy
Author(s)
Pelikan, Martin
Issue Date
2002
Doctoral Committee Chair(s)
Goldberg, David E.
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Operations Research
Language
eng
Abstract
The dissertation proposes the Bayesian optimization algorithm (BOA), which uses Bayesian networks to model the promising solutions found so far and sample new candidate solutions. BOA is theoretically and empirically shown to be capable of both learning a proper decomposition of the problem and exploiting the learned decomposition to ensure robust and scalable search for the optimum across a wide range of problems. The dissertation then identifies important features that must be incorporated into the basic BOA to solve problems that are not decomposable on a single level, but that can still be solved by decomposition over multiple levels of difficulty. Hierarchical BOA extends BOA by incorporating those features for robust and scalable optimization of hierarchically decomposable problems. A class of problems called hierarchical traps is then proposed to test the ability of optimizers to learn and exploit hierarchical decomposition. Hierarchical BOA passes the test and is shown to solve hierarchical traps and other hierarchical problems in a scalable manner. Finally, the dissertation applies hierarchical BOA to two important classes of problems of statistical physics and artificial intelligence---Ising spin-glass systems and maximum satisfiability. Experiments show that even without requiring any prior problem-specific knowledge about the structure of the problem at hand or its properties, hierarchical BOA is capable of achieving comparable or better performance than other state-of-the-art methods specializing in solving the examined classes of problems.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
