Automatic selection for general surrogate models
Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Ben Salem, Malek [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2018 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Springer-Verlag GmbH Germany, part of Springer Nature 2018 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Structural and multidisciplinary optimization - Springer Berlin Heidelberg, 2000, 58(2018), 2 vom: 20. Feb., Seite 719-734 |
|---|---|
| Übergeordnetes Werk: |
volume:58 ; year:2018 ; number:2 ; day:20 ; month:02 ; pages:719-734 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00158-018-1925-3 |
|---|
| Katalog-ID: |
OLC2051786852 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2051786852 | ||
| 003 | DE-627 | ||
| 005 | 20230401065238.0 | ||
| 007 | tu | ||
| 008 | 200820s2018 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00158-018-1925-3 |2 doi | |
| 035 | |a (DE-627)OLC2051786852 | ||
| 035 | |a (DE-He213)s00158-018-1925-3-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 510 |q VZ |
| 084 | |a 11 |2 ssgn | ||
| 084 | |a 50.03$jMethoden und Techniken der Ingenieurwissenschaften |2 bkl | ||
| 100 | 1 | |a Ben Salem, Malek |e verfasserin |0 (orcid)0000-0003-0659-2302 |4 aut | |
| 245 | 1 | 0 | |a Automatic selection for general surrogate models |
| 264 | 1 | |c 2018 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © Springer-Verlag GmbH Germany, part of Springer Nature 2018 | ||
| 520 | |a Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. | ||
| 650 | 4 | |a Surrogate modeling | |
| 650 | 4 | |a Multiple surrogate models | |
| 650 | 4 | |a Surrogate model selection | |
| 650 | 4 | |a Cross-validation errors | |
| 700 | 1 | |a Tomaso, Lionel |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Structural and multidisciplinary optimization |d Springer Berlin Heidelberg, 2000 |g 58(2018), 2 vom: 20. Feb., Seite 719-734 |w (DE-627)312415958 |w (DE-600)2009366-4 |w (DE-576)090895207 |x 1615-147X |7 nnns |
| 773 | 1 | 8 | |g volume:58 |g year:2018 |g number:2 |g day:20 |g month:02 |g pages:719-734 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00158-018-1925-3 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a SSG-OPC-MAT | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 936 | b | k | |a 50.03$jMethoden und Techniken der Ingenieurwissenschaften |q VZ |0 181571455 |0 (DE-625)181571455 |
| 951 | |a AR | ||
| 952 | |d 58 |j 2018 |e 2 |b 20 |c 02 |h 719-734 | ||
| author_variant |
s m b sm smb l t lt |
|---|---|
| matchkey_str |
article:1615147X:2018----::uoaislcinognrlu |
| hierarchy_sort_str |
2018 |
| bklnumber |
50.03$jMethoden und Techniken der Ingenieurwissenschaften |
| publishDate |
2018 |
| allfields |
10.1007/s00158-018-1925-3 doi (DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p DE-627 ger DE-627 rakwb eng 510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Ben Salem, Malek verfasserin (orcid)0000-0003-0659-2302 aut Automatic selection for general surrogate models 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors Tomaso, Lionel aut Enthalten in Structural and multidisciplinary optimization Springer Berlin Heidelberg, 2000 58(2018), 2 vom: 20. Feb., Seite 719-734 (DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 1615-147X nnns volume:58 year:2018 number:2 day:20 month:02 pages:719-734 https://doi.org/10.1007/s00158-018-1925-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 50.03$jMethoden und Techniken der Ingenieurwissenschaften VZ 181571455 (DE-625)181571455 AR 58 2018 2 20 02 719-734 |
| spelling |
10.1007/s00158-018-1925-3 doi (DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p DE-627 ger DE-627 rakwb eng 510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Ben Salem, Malek verfasserin (orcid)0000-0003-0659-2302 aut Automatic selection for general surrogate models 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors Tomaso, Lionel aut Enthalten in Structural and multidisciplinary optimization Springer Berlin Heidelberg, 2000 58(2018), 2 vom: 20. Feb., Seite 719-734 (DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 1615-147X nnns volume:58 year:2018 number:2 day:20 month:02 pages:719-734 https://doi.org/10.1007/s00158-018-1925-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 50.03$jMethoden und Techniken der Ingenieurwissenschaften VZ 181571455 (DE-625)181571455 AR 58 2018 2 20 02 719-734 |
| allfields_unstemmed |
10.1007/s00158-018-1925-3 doi (DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p DE-627 ger DE-627 rakwb eng 510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Ben Salem, Malek verfasserin (orcid)0000-0003-0659-2302 aut Automatic selection for general surrogate models 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors Tomaso, Lionel aut Enthalten in Structural and multidisciplinary optimization Springer Berlin Heidelberg, 2000 58(2018), 2 vom: 20. Feb., Seite 719-734 (DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 1615-147X nnns volume:58 year:2018 number:2 day:20 month:02 pages:719-734 https://doi.org/10.1007/s00158-018-1925-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 50.03$jMethoden und Techniken der Ingenieurwissenschaften VZ 181571455 (DE-625)181571455 AR 58 2018 2 20 02 719-734 |
| allfieldsGer |
10.1007/s00158-018-1925-3 doi (DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p DE-627 ger DE-627 rakwb eng 510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Ben Salem, Malek verfasserin (orcid)0000-0003-0659-2302 aut Automatic selection for general surrogate models 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors Tomaso, Lionel aut Enthalten in Structural and multidisciplinary optimization Springer Berlin Heidelberg, 2000 58(2018), 2 vom: 20. Feb., Seite 719-734 (DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 1615-147X nnns volume:58 year:2018 number:2 day:20 month:02 pages:719-734 https://doi.org/10.1007/s00158-018-1925-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 50.03$jMethoden und Techniken der Ingenieurwissenschaften VZ 181571455 (DE-625)181571455 AR 58 2018 2 20 02 719-734 |
| allfieldsSound |
10.1007/s00158-018-1925-3 doi (DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p DE-627 ger DE-627 rakwb eng 510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Ben Salem, Malek verfasserin (orcid)0000-0003-0659-2302 aut Automatic selection for general surrogate models 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors Tomaso, Lionel aut Enthalten in Structural and multidisciplinary optimization Springer Berlin Heidelberg, 2000 58(2018), 2 vom: 20. Feb., Seite 719-734 (DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 1615-147X nnns volume:58 year:2018 number:2 day:20 month:02 pages:719-734 https://doi.org/10.1007/s00158-018-1925-3 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 50.03$jMethoden und Techniken der Ingenieurwissenschaften VZ 181571455 (DE-625)181571455 AR 58 2018 2 20 02 719-734 |
| language |
English |
| source |
Enthalten in Structural and multidisciplinary optimization 58(2018), 2 vom: 20. Feb., Seite 719-734 volume:58 year:2018 number:2 day:20 month:02 pages:719-734 |
| sourceStr |
Enthalten in Structural and multidisciplinary optimization 58(2018), 2 vom: 20. Feb., Seite 719-734 volume:58 year:2018 number:2 day:20 month:02 pages:719-734 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors |
| dewey-raw |
510 |
| isfreeaccess_bool |
false |
| container_title |
Structural and multidisciplinary optimization |
| authorswithroles_txt_mv |
Ben Salem, Malek @@aut@@ Tomaso, Lionel @@aut@@ |
| publishDateDaySort_date |
2018-02-20T00:00:00Z |
| hierarchy_top_id |
312415958 |
| dewey-sort |
3510 |
| id |
OLC2051786852 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2051786852</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230401065238.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00158-018-1925-3</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2051786852</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00158-018-1925-3-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">11</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.03$jMethoden und Techniken der Ingenieurwissenschaften</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ben Salem, Malek</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0659-2302</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automatic selection for general surrogate models</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer-Verlag GmbH Germany, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Surrogate modeling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multiple surrogate models</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Surrogate model selection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-validation errors</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tomaso, Lionel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Structural and multidisciplinary optimization</subfield><subfield code="d">Springer Berlin Heidelberg, 2000</subfield><subfield code="g">58(2018), 2 vom: 20. Feb., Seite 719-734</subfield><subfield code="w">(DE-627)312415958</subfield><subfield code="w">(DE-600)2009366-4</subfield><subfield code="w">(DE-576)090895207</subfield><subfield code="x">1615-147X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:58</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:2</subfield><subfield code="g">day:20</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:719-734</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00158-018-1925-3</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.03$jMethoden und Techniken der Ingenieurwissenschaften</subfield><subfield code="q">VZ</subfield><subfield code="0">181571455</subfield><subfield code="0">(DE-625)181571455</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">58</subfield><subfield code="j">2018</subfield><subfield code="e">2</subfield><subfield code="b">20</subfield><subfield code="c">02</subfield><subfield code="h">719-734</subfield></datafield></record></collection>
|
| author |
Ben Salem, Malek |
| spellingShingle |
Ben Salem, Malek ddc 510 ssgn 11 bkl 50.03$jMethoden und Techniken der Ingenieurwissenschaften misc Surrogate modeling misc Multiple surrogate models misc Surrogate model selection misc Cross-validation errors Automatic selection for general surrogate models |
| authorStr |
Ben Salem, Malek |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)312415958 |
| format |
Article |
| dewey-ones |
510 - Mathematics |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1615-147X |
| topic_title |
510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl Automatic selection for general surrogate models Surrogate modeling Multiple surrogate models Surrogate model selection Cross-validation errors |
| topic |
ddc 510 ssgn 11 bkl 50.03$jMethoden und Techniken der Ingenieurwissenschaften misc Surrogate modeling misc Multiple surrogate models misc Surrogate model selection misc Cross-validation errors |
| topic_unstemmed |
ddc 510 ssgn 11 bkl 50.03$jMethoden und Techniken der Ingenieurwissenschaften misc Surrogate modeling misc Multiple surrogate models misc Surrogate model selection misc Cross-validation errors |
| topic_browse |
ddc 510 ssgn 11 bkl 50.03$jMethoden und Techniken der Ingenieurwissenschaften misc Surrogate modeling misc Multiple surrogate models misc Surrogate model selection misc Cross-validation errors |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Structural and multidisciplinary optimization |
| hierarchy_parent_id |
312415958 |
| dewey-tens |
510 - Mathematics |
| hierarchy_top_title |
Structural and multidisciplinary optimization |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)312415958 (DE-600)2009366-4 (DE-576)090895207 |
| title |
Automatic selection for general surrogate models |
| ctrlnum |
(DE-627)OLC2051786852 (DE-He213)s00158-018-1925-3-p |
| title_full |
Automatic selection for general surrogate models |
| author_sort |
Ben Salem, Malek |
| journal |
Structural and multidisciplinary optimization |
| journalStr |
Structural and multidisciplinary optimization |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
500 - Science |
| recordtype |
marc |
| publishDateSort |
2018 |
| contenttype_str_mv |
txt |
| container_start_page |
719 |
| author_browse |
Ben Salem, Malek Tomaso, Lionel |
| container_volume |
58 |
| class |
510 VZ 11 ssgn 50.03$jMethoden und Techniken der Ingenieurwissenschaften bkl |
| format_se |
Aufsätze |
| author-letter |
Ben Salem, Malek |
| doi_str_mv |
10.1007/s00158-018-1925-3 |
| normlink |
(ORCID)0000-0003-0659-2302 181571455 |
| normlink_prefix_str_mv |
(orcid)0000-0003-0659-2302 181571455 (DE-625)181571455 |
| dewey-full |
510 |
| title_sort |
automatic selection for general surrogate models |
| title_auth |
Automatic selection for general surrogate models |
| abstract |
Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. © Springer-Verlag GmbH Germany, part of Springer Nature 2018 |
| abstractGer |
Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. © Springer-Verlag GmbH Germany, part of Springer Nature 2018 |
| abstract_unstemmed |
Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting. © Springer-Verlag GmbH Germany, part of Springer Nature 2018 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
2 |
| title_short |
Automatic selection for general surrogate models |
| url |
https://doi.org/10.1007/s00158-018-1925-3 |
| remote_bool |
false |
| author2 |
Tomaso, Lionel |
| author2Str |
Tomaso, Lionel |
| ppnlink |
312415958 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00158-018-1925-3 |
| up_date |
2024-07-04T05:17:57.981Z |
| _version_ |
1803624411805253632 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2051786852</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230401065238.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00158-018-1925-3</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2051786852</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00158-018-1925-3-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">11</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.03$jMethoden und Techniken der Ingenieurwissenschaften</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ben Salem, Malek</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-0659-2302</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automatic selection for general surrogate models</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer-Verlag GmbH Germany, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Surrogate modeling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multiple surrogate models</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Surrogate model selection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-validation errors</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tomaso, Lionel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Structural and multidisciplinary optimization</subfield><subfield code="d">Springer Berlin Heidelberg, 2000</subfield><subfield code="g">58(2018), 2 vom: 20. Feb., Seite 719-734</subfield><subfield code="w">(DE-627)312415958</subfield><subfield code="w">(DE-600)2009366-4</subfield><subfield code="w">(DE-576)090895207</subfield><subfield code="x">1615-147X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:58</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:2</subfield><subfield code="g">day:20</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:719-734</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00158-018-1925-3</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.03$jMethoden und Techniken der Ingenieurwissenschaften</subfield><subfield code="q">VZ</subfield><subfield code="0">181571455</subfield><subfield code="0">(DE-625)181571455</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">58</subfield><subfield code="j">2018</subfield><subfield code="e">2</subfield><subfield code="b">20</subfield><subfield code="c">02</subfield><subfield code="h">719-734</subfield></datafield></record></collection>
|
| score |
7.3993654 |