Algorithm Configuration: Learning Policies for the Quick Termination of Poor Performers

One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations that eventually do well on the long runs. We consider the problem of selecting the top performing configurations of Conditional Markov Chain S...

Full description

Saved in:
Bibliographic Details
Published inLearning and Intelligent Optimization Vol. 11353; pp. 220 - 224
Main Authors Karapetyan, Daniel, Parkes, Andrew J., Stützle, Thomas
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 01.01.2019
Springer International Publishing
SeriesLecture Notes in Computer Science
Online AccessGet full text
ISBN3030053474
9783030053475
ISSN0302-9743
1611-3349
DOI10.1007/978-3-030-05348-2_20

Cover

Abstract One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations that eventually do well on the long runs. We consider the problem of selecting the top performing configurations of Conditional Markov Chain Search (CMCS), a general algorithm schema that includes, for example, VNS. We investigate how the structure of performance on short tests links with those on long tests, showing that significant differences arise between test domains. We propose a “performance envelope” method to exploit the links; that learns when runs should be terminated, but that automatically adapts to the domain.
AbstractList One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations that eventually do well on the long runs. We consider the problem of selecting the top performing configurations of Conditional Markov Chain Search (CMCS), a general algorithm schema that includes, for example, VNS. We investigate how the structure of performance on short tests links with those on long tests, showing that significant differences arise between test domains. We propose a “performance envelope” method to exploit the links; that learns when runs should be terminated, but that automatically adapts to the domain.
Author Karapetyan, Daniel
Parkes, Andrew J.
Stützle, Thomas
Author_xml – sequence: 1
  givenname: Daniel
  surname: Karapetyan
  fullname: Karapetyan, Daniel
  email: daniel.karapetyan@gmail.com
– sequence: 2
  givenname: Andrew J.
  surname: Parkes
  fullname: Parkes, Andrew J.
– sequence: 3
  givenname: Thomas
  surname: Stützle
  fullname: Stützle, Thomas
BookMark eNo1kN1OAjEQhauiEZA38GJfoNp2-rP1jhD_EhIxwXjZLN3usgIttsv7W1CvZnLmnMnMN0IDH7xD6JaSO0qIuteqxIAJEEwE8BIzw8gZmmQZsnjS2DkaUkkpBuD6Ao3-B4oP0DD3DGvF4QqNKCkpEM4JvUaTlL4IIYyVXAoxRJ_TbRti1693xSz4pmsPseq74B-Kuaui73xbLMK2s51LRRNi0a9d8X7o7KZYurjr_MlchCa78nThYjbtXEw36LKptslN_uoYfTw9LmcveP72_DqbznELnPVYQl03VEtVq5W01AHjNdGl5SJfvBKN1mCZUtQKzpyj1Fme_xCyYbSspJAwRux3b9rHfKyLZhXCJhlKzJGjycAMmEzDnJiZI8cc4r-hfQzfB5d6444p63wfq61dV_s-v2CEZlwobqjmhgHAD-N2chU
ContentType Book Chapter
Copyright Springer Nature Switzerland AG 2019
Copyright_xml – notice: Springer Nature Switzerland AG 2019
DBID FFUUA
DEWEY 6.31
DOI 10.1007/978-3-030-05348-2_20
DatabaseName ProQuest Ebook Central - Book Chapters - Demo use only
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9783030053482
3030053482
EISSN 1611-3349
Editor Battiti, Roberto
Brunato, Mauro
Kotsireas, Ilias
Pardalos, Panos M
Editor_xml – sequence: 1
  fullname: Pardalos, Panos M
– sequence: 2
  fullname: Battiti, Roberto
– sequence: 3
  fullname: Brunato, Mauro
– sequence: 4
  fullname: Kotsireas, Ilias
EndPage 224
ExternalDocumentID EBC5924574_194_233
GroupedDBID 0D6
0DA
38.
AABBV
AEDXK
AEJLV
AEKFX
AEZAY
AIFIR
ALEXF
ALMA_UNASSIGNED_HOLDINGS
AYMPB
BBABE
CXBFT
CZZ
EXGDT
FCSXQ
FFUUA
I4C
IEZ
MGZZY
NSQWD
OORQV
SBO
TPJZQ
TSXQS
Z81
Z83
Z88
-DT
-~X
29L
2HA
2HV
ACGFS
ADCXD
EJD
F5P
LAS
LDH
P2P
RSU
~02
ID FETCH-LOGICAL-g342t-63ddf1967d7b6c1e324d098c45130b5f993c2771c542ee11ec444056f218a6563
ISBN 3030053474
9783030053475
ISSN 0302-9743
IngestDate Tue Jul 29 20:15:18 EDT 2025
Thu May 29 16:31:05 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
LCCallNum QA76.9.A43
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-g342t-63ddf1967d7b6c1e324d098c45130b5f993c2771c542ee11ec444056f218a6563
OCLC 1081304401
OpenAccessLink https://dipot.ulb.ac.be/dspace/bitstream/2013/283882/3/cmcs-tuning-lion2018.pdf
PQID EBC5924574_194_233
PageCount 5
ParticipantIDs springer_books_10_1007_978_3_030_05348_2_20
proquest_ebookcentralchapters_5924574_194_233
PublicationCentury 2000
PublicationDate 2019-01-01
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – month: 01
  year: 2019
  text: 2019-01-01
  day: 01
PublicationDecade 2010
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
– name: Cham
PublicationSeriesSubtitle Theoretical Computer Science and General Issues
PublicationSeriesTitle Lecture Notes in Computer Science
PublicationSeriesTitleAlternate Lect.Notes Computer
PublicationSubtitle 12th International Conference, LION 12, Kalamata, Greece, June 10-15, 2018, Revised Selected Papers
PublicationTitle Learning and Intelligent Optimization
PublicationYear 2019
Publisher Springer International Publishing AG
Springer International Publishing
Publisher_xml – name: Springer International Publishing AG
– name: Springer International Publishing
RelatedPersons Kleinberg, Jon M.
Mattern, Friedemann
Naor, Moni
Mitchell, John C.
Terzopoulos, Demetri
Steffen, Bernhard
Pandu Rangan, C.
Kanade, Takeo
Kittler, Josef
Hutchison, David
Tygar, Doug
RelatedPersons_xml – sequence: 1
  givenname: David
  surname: Hutchison
  fullname: Hutchison, David
– sequence: 2
  givenname: Takeo
  surname: Kanade
  fullname: Kanade, Takeo
– sequence: 3
  givenname: Josef
  surname: Kittler
  fullname: Kittler, Josef
– sequence: 4
  givenname: Jon M.
  surname: Kleinberg
  fullname: Kleinberg, Jon M.
– sequence: 5
  givenname: Friedemann
  surname: Mattern
  fullname: Mattern, Friedemann
– sequence: 6
  givenname: John C.
  surname: Mitchell
  fullname: Mitchell, John C.
– sequence: 7
  givenname: Moni
  surname: Naor
  fullname: Naor, Moni
– sequence: 8
  givenname: C.
  surname: Pandu Rangan
  fullname: Pandu Rangan, C.
– sequence: 9
  givenname: Bernhard
  surname: Steffen
  fullname: Steffen, Bernhard
– sequence: 10
  givenname: Demetri
  surname: Terzopoulos
  fullname: Terzopoulos, Demetri
– sequence: 11
  givenname: Doug
  surname: Tygar
  fullname: Tygar, Doug
SSID ssj0002284655
ssj0002792
Score 2.165543
Snippet One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations...
SourceID springer
proquest
SourceType Publisher
StartPage 220
Title Algorithm Configuration: Learning Policies for the Quick Termination of Poor Performers
URI http://ebookcentral.proquest.com/lib/SITE_ID/reader.action?docID=5924574&ppg=233
http://link.springer.com/10.1007/978-3-030-05348-2_20
Volume 11353
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnZ3PT9swFMet0V0QB2Ab4rd84FZ5Io5_JNwKKiA0MSaVjZtVO3apNlqppBf-ep6TOE2iXtglqtLEsvxx7Ofn931G6Cw1lLmMOeITuxAmhSHjVGriM4G7caKd1UWU7724fWR3T_wpHO9eqUty_d28rdWV_A9VuAdcvUr2A2TrQuEG_Aa-cAXCcO0Yv203a6leDk6NMqI3ZNbM-z9hFHip5JXNHjH4N5kvpvnzSyHzm06Wizqyoy6rSBMMi-c6-vDXcmr-9kdlyEywLh_m8O9DKTmoIuiD58CLlVqeg-A57PgeG-6vwU1rtQmznf9mWXnUST18-pMz1g7GzfgLeJX4dwGgouerySdsuNMyHUYn9_Xw8orDApFLpqKUKXhoA23IhPfQ58Hw7sfv2ptGYZYVnHvxTqhkmfWxUemGcHJdnVpLjM6ueGFsjHbQlhegYK8MgVruok929gVth-M3cDUaf0V_aqC4BfQCB5w44MRACgNOXODEDZx47rDHiVc4v6HH6-Ho6pZU52SQScxoTkScZQ5GUplJLUxkwUbOztPEMA4GiuYOTFBDpYwMZ9TaKLKGMbDThQPzbgzfaLyHerP5zO4jbLWIY8k1pWMKZkuWJrFIaEqjWESZS5IDREIjqWI3vwohNmWTvKoOrgPUDy2p_OOvKqTJBgQqVoBAFQiUR3D4wdKP0OaqXx-jXr5Y2hOwEXN9WnWQd0VnYnk
linkProvider Library Specific Holdings
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.title=Learning+and+Intelligent+Optimization&rft.atitle=Algorithm+Configuration%3A+Learning+Policies+for+the+Quick+Termination+of+Poor+Performers&rft.date=2019-01-01&rft.pub=Springer+International+Publishing+AG&rft.isbn=9783030053475&rft.volume=11353&rft_id=info:doi/10.1007%2F978-3-030-05348-2_20&rft.externalDBID=233&rft.externalDocID=EBC5924574_194_233
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Febookcentral.proquest.com%2Fcovers%2F5924574-l.jpg