抄録
Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude faster than lexicase selection while achieving a competitive quality of solutions. Tests on a number of regression datasets show that BTS compares well with lexicase selection in terms of mean absolute error while having a speed-up of up to 25 times. Surprisingly, BTS and lexicase selection have almost no difference in both diversity and performance. This reveals that batches and ordered test cases are completely different mechanisms which share the same general principle fostering the specialization of individuals. This work introduces an efficient algorithm that sheds light onto the main principles behind the success of lexicase, potentially opening up a new range of possibilities for algorithms to come.
| 元の言語 | 英語 |
|---|---|
| ホスト出版物のタイトル | GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference |
| 出版者 | Association for Computing Machinery, Inc |
| ページ | 994-1002 |
| ページ数 | 9 |
| ISBN（電子版） | 9781450361118 |
| DOI | |
| 出版物ステータス | 出版済み - 7 13 2019 |
| イベント | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, チェコ共和国 継続期間: 7 13 2019 → 7 17 2019 |
出版物シリーズ
| 名前 | GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference |
|---|
会議
| 会議 | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 |
|---|---|
| 国 | チェコ共和国 |
| 市 | Prague |
| 期間 | 7/13/19 → 7/17/19 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computational Mathematics
これを引用
Batch tournament selection for genetic programming. / De Melo, Vinícius V.; Vargas, Danilo Vasconcellos; Banzhaf, Wolfgang.
GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, Inc, 2019. p. 994-1002 (GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference).研究成果: 著書/レポートタイプへの貢献 › 会議での発言
}
TY - GEN
T1 - Batch tournament selection for genetic programming
AU - De Melo, Vinícius V.
AU - Vargas, Danilo Vasconcellos
AU - Banzhaf, Wolfgang
PY - 2019/7/13
Y1 - 2019/7/13
N2 - Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude faster than lexicase selection while achieving a competitive quality of solutions. Tests on a number of regression datasets show that BTS compares well with lexicase selection in terms of mean absolute error while having a speed-up of up to 25 times. Surprisingly, BTS and lexicase selection have almost no difference in both diversity and performance. This reveals that batches and ordered test cases are completely different mechanisms which share the same general principle fostering the specialization of individuals. This work introduces an efficient algorithm that sheds light onto the main principles behind the success of lexicase, potentially opening up a new range of possibilities for algorithms to come.
AB - Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude faster than lexicase selection while achieving a competitive quality of solutions. Tests on a number of regression datasets show that BTS compares well with lexicase selection in terms of mean absolute error while having a speed-up of up to 25 times. Surprisingly, BTS and lexicase selection have almost no difference in both diversity and performance. This reveals that batches and ordered test cases are completely different mechanisms which share the same general principle fostering the specialization of individuals. This work introduces an efficient algorithm that sheds light onto the main principles behind the success of lexicase, potentially opening up a new range of possibilities for algorithms to come.
UR - http://www.scopus.com/inward/record.url?scp=85072324318&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072324318&partnerID=8YFLogxK
U2 - 10.1145/3321707.3321793
DO - 10.1145/3321707.3321793
M3 - Conference contribution
AN - SCOPUS:85072324318
T3 - GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference
SP - 994
EP - 1002
BT - GECCO 2019 - Proceedings of the 2019 Genetic and Evolutionary Computation Conference
PB - Association for Computing Machinery, Inc
ER -