Parametric Regression Through Genetic Programming. Banks, E. R., Hayes, J., & Nunez, E. In Late Breaking Papers at the 2004 Genetic and Evolutionary Computation Conference, Seattle, Washington, USA, 26 July, 2004. Paper abstract bibtex Parametric regression in genetic programming can substantially speed up the search for solutions. Paradoxically, the same technique has difficulty finding a true optimum solution. The parametric formulation of a problem results in a fitness landscape that looks like an inverted brush with many bristles of almost equal length (individuals of high fitness), but with only one bristle that is very slightly longer than the rest, the optimum solution. As such it is easy to find very good, even outstanding solutions, but very difficult to locate the optimum solution. In this paper parametric regression is applied to a minimum-time-to-target problem. The solution is equivalent to the classical brachistochrone. Two formulations were tried: a parametric regression and the classical symbolic regression formulation. The parametric approach was superior without exception. We speculate the parametric approach is more generally applicable to other problems and suggest areas for more research.
@inproceedings{banks:2004:lbp,
abstract = {Parametric regression in genetic programming can
substantially speed up the search for solutions.
Paradoxically, the same technique has difficulty
finding a true optimum solution. The parametric
formulation of a problem results in a fitness landscape
that looks like an inverted brush with many bristles of
almost equal length (individuals of high fitness), but
with only one bristle that is very slightly longer than
the rest, the optimum solution. As such it is easy to
find very good, even outstanding solutions, but very
difficult to locate the optimum solution. In this paper
parametric regression is applied to a
minimum-time-to-target problem. The solution is
equivalent to the classical brachistochrone. Two
formulations were tried: a parametric regression and
the classical symbolic regression formulation. The
parametric approach was superior without exception. We
speculate the parametric approach is more generally
applicable to other problems and suggest areas for more
research.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Seattle, Washington, USA},
author = {Banks, Edwin Roger and Hayes, James and Nunez, Edwin},
biburl = {https://www.bibsonomy.org/bibtex/24423e8a00c0bfaa70b88843246cc073a/brazovayeye},
booktitle = {Late Breaking Papers at the 2004 Genetic and
Evolutionary Computation Conference},
editor = {Keijzer, Maarten},
interhash = {20db3fd025cf5b4b47845b834d6a844c},
intrahash = {4423e8a00c0bfaa70b88843246cc073a},
keywords = {genetic algorithms, programming},
month = {26 July},
notes = {Part of \cite{keijzer:2004:GECCO:lbp}},
timestamp = {2008-06-19T17:36:11.000+0200},
title = {Parametric Regression Through Genetic Programming},
url = {http://www.cs.bham.ac.uk/~wbl/biblio/gecco2004/LBP001.pdf},
year = 2004
}
Downloads: 0
{"_id":"WGqB2hZeSSK4B8kj9","bibbaseid":"banks-hayes-nunez-parametricregressionthroughgeneticprogramming-2004","authorIDs":[],"author_short":["Banks, E. R.","Hayes, J.","Nunez, E."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Parametric regression in genetic programming can substantially speed up the search for solutions. Paradoxically, the same technique has difficulty finding a true optimum solution. The parametric formulation of a problem results in a fitness landscape that looks like an inverted brush with many bristles of almost equal length (individuals of high fitness), but with only one bristle that is very slightly longer than the rest, the optimum solution. As such it is easy to find very good, even outstanding solutions, but very difficult to locate the optimum solution. In this paper parametric regression is applied to a minimum-time-to-target problem. The solution is equivalent to the classical brachistochrone. Two formulations were tried: a parametric regression and the classical symbolic regression formulation. The parametric approach was superior without exception. We speculate the parametric approach is more generally applicable to other problems and suggest areas for more research.","added-at":"2008-06-19T17:35:00.000+0200","address":"Seattle, Washington, USA","author":[{"propositions":[],"lastnames":["Banks"],"firstnames":["Edwin","Roger"],"suffixes":[]},{"propositions":[],"lastnames":["Hayes"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Nunez"],"firstnames":["Edwin"],"suffixes":[]}],"biburl":"https://www.bibsonomy.org/bibtex/24423e8a00c0bfaa70b88843246cc073a/brazovayeye","booktitle":"Late Breaking Papers at the 2004 Genetic and Evolutionary Computation Conference","editor":[{"propositions":[],"lastnames":["Keijzer"],"firstnames":["Maarten"],"suffixes":[]}],"interhash":"20db3fd025cf5b4b47845b834d6a844c","intrahash":"4423e8a00c0bfaa70b88843246cc073a","keywords":"genetic algorithms, programming","month":"26 July","notes":"Part of i̧tekeijzer:2004:GECCO:lbp","timestamp":"2008-06-19T17:36:11.000+0200","title":"Parametric Regression Through Genetic Programming","url":"http://www.cs.bham.ac.uk/~wbl/biblio/gecco2004/LBP001.pdf","year":"2004","bibtex":"@inproceedings{banks:2004:lbp,\n abstract = {Parametric regression in genetic programming can\n substantially speed up the search for solutions.\n Paradoxically, the same technique has difficulty\n finding a true optimum solution. The parametric\n formulation of a problem results in a fitness landscape\n that looks like an inverted brush with many bristles of\n almost equal length (individuals of high fitness), but\n with only one bristle that is very slightly longer than\n the rest, the optimum solution. As such it is easy to\n find very good, even outstanding solutions, but very\n difficult to locate the optimum solution. In this paper\n parametric regression is applied to a\n minimum-time-to-target problem. The solution is\n equivalent to the classical brachistochrone. Two\n formulations were tried: a parametric regression and\n the classical symbolic regression formulation. The\n parametric approach was superior without exception. We\n speculate the parametric approach is more generally\n applicable to other problems and suggest areas for more\n research.},\n added-at = {2008-06-19T17:35:00.000+0200},\n address = {Seattle, Washington, USA},\n author = {Banks, Edwin Roger and Hayes, James and Nunez, Edwin},\n biburl = {https://www.bibsonomy.org/bibtex/24423e8a00c0bfaa70b88843246cc073a/brazovayeye},\n booktitle = {Late Breaking Papers at the 2004 Genetic and\n Evolutionary Computation Conference},\n editor = {Keijzer, Maarten},\n interhash = {20db3fd025cf5b4b47845b834d6a844c},\n intrahash = {4423e8a00c0bfaa70b88843246cc073a},\n keywords = {genetic algorithms, programming},\n month = {26 July},\n notes = {Part of \\cite{keijzer:2004:GECCO:lbp}},\n timestamp = {2008-06-19T17:36:11.000+0200},\n title = {Parametric Regression Through Genetic Programming},\n url = {http://www.cs.bham.ac.uk/~wbl/biblio/gecco2004/LBP001.pdf},\n year = 2004\n}\n\n","author_short":["Banks, E. R.","Hayes, J.","Nunez, E."],"editor_short":["Keijzer, M."],"key":"banks:2004:lbp","id":"banks:2004:lbp","bibbaseid":"banks-hayes-nunez-parametricregressionthroughgeneticprogramming-2004","role":"author","urls":{"Paper":"http://www.cs.bham.ac.uk/~wbl/biblio/gecco2004/LBP001.pdf"},"keyword":["genetic algorithms","programming"],"downloads":0},"bibtype":"inproceedings","biburl":"http://www.bibsonomy.org/bib/author/banks?items=1000","creationDate":"2020-11-09T04:30:05.624Z","downloads":0,"keywords":["genetic algorithms","programming"],"search_terms":["parametric","regression","through","genetic","programming","banks","hayes","nunez"],"title":"Parametric Regression Through Genetic Programming","year":2004,"dataSources":["4mnhe87Gt4h7SC73t"]}