Adaptive Algorithms for Meta-Induction
Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting a...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Ortner, Ronald [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s) 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Journal for general philosophy of science - Springer Netherlands, 1990, 54(2022), 3 vom: 07. Okt., Seite 433-450 |
|---|---|
| Übergeordnetes Werk: |
volume:54 ; year:2022 ; number:3 ; day:07 ; month:10 ; pages:433-450 |
| Links: |
|---|
| DOI / URN: |
10.1007/s10838-021-09590-2 |
|---|
| Katalog-ID: |
OLC2145645810 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2145645810 | ||
| 003 | DE-627 | ||
| 005 | 20240118105845.0 | ||
| 007 | tu | ||
| 008 | 240118s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10838-021-09590-2 |2 doi | |
| 035 | |a (DE-627)OLC2145645810 | ||
| 035 | |a (DE-He213)s10838-021-09590-2-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 000 |a 500 |a 100 |q VZ |
| 082 | 0 | 4 | |a 050 |q VZ |
| 084 | |a 19,2 |a 24 |a 5,1 |2 ssgn | ||
| 084 | |a LING |q DE-30 |2 fid | ||
| 100 | 1 | |a Ortner, Ronald |e verfasserin |0 (orcid)0000-0001-6033-2208 |4 aut | |
| 245 | 1 | 0 | |a Adaptive Algorithms for Meta-Induction |
| 264 | 1 | |c 2022 | |
| 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 © The Author(s) 2022 | ||
| 520 | |a Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. | ||
| 650 | 4 | |a Online learning | |
| 650 | 4 | |a Regret | |
| 650 | 4 | |a Prediction with expert advice | |
| 650 | 4 | |a Multi-armed bandit problem | |
| 773 | 0 | 8 | |i Enthalten in |t Journal for general philosophy of science |d Springer Netherlands, 1990 |g 54(2022), 3 vom: 07. Okt., Seite 433-450 |w (DE-627)130910597 |w (DE-600)1048887-X |w (DE-576)025001191 |x 0925-4560 |7 nnns |
| 773 | 1 | 8 | |g volume:54 |g year:2022 |g number:3 |g day:07 |g month:10 |g pages:433-450 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s10838-021-09590-2 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a FID-LING | ||
| 912 | |a SSG-OLC-PHI | ||
| 912 | |a SSG-OPC-BBI | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_50 | ||
| 912 | |a GBV_ILN_171 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4012 | ||
| 912 | |a GBV_ILN_4318 | ||
| 912 | |a GBV_ILN_4385 | ||
| 951 | |a AR | ||
| 952 | |d 54 |j 2022 |e 3 |b 07 |c 10 |h 433-450 | ||
| author_variant |
r o ro |
|---|---|
| matchkey_str |
article:09254560:2022----::dpieloihsomt |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s10838-021-09590-2 doi (DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p DE-627 ger DE-627 rakwb eng 000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Ortner, Ronald verfasserin (orcid)0000-0001-6033-2208 aut Adaptive Algorithms for Meta-Induction 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. Online learning Regret Prediction with expert advice Multi-armed bandit problem Enthalten in Journal for general philosophy of science Springer Netherlands, 1990 54(2022), 3 vom: 07. Okt., Seite 433-450 (DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 0925-4560 nnns volume:54 year:2022 number:3 day:07 month:10 pages:433-450 https://doi.org/10.1007/s10838-021-09590-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 AR 54 2022 3 07 10 433-450 |
| spelling |
10.1007/s10838-021-09590-2 doi (DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p DE-627 ger DE-627 rakwb eng 000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Ortner, Ronald verfasserin (orcid)0000-0001-6033-2208 aut Adaptive Algorithms for Meta-Induction 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. Online learning Regret Prediction with expert advice Multi-armed bandit problem Enthalten in Journal for general philosophy of science Springer Netherlands, 1990 54(2022), 3 vom: 07. Okt., Seite 433-450 (DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 0925-4560 nnns volume:54 year:2022 number:3 day:07 month:10 pages:433-450 https://doi.org/10.1007/s10838-021-09590-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 AR 54 2022 3 07 10 433-450 |
| allfields_unstemmed |
10.1007/s10838-021-09590-2 doi (DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p DE-627 ger DE-627 rakwb eng 000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Ortner, Ronald verfasserin (orcid)0000-0001-6033-2208 aut Adaptive Algorithms for Meta-Induction 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. Online learning Regret Prediction with expert advice Multi-armed bandit problem Enthalten in Journal for general philosophy of science Springer Netherlands, 1990 54(2022), 3 vom: 07. Okt., Seite 433-450 (DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 0925-4560 nnns volume:54 year:2022 number:3 day:07 month:10 pages:433-450 https://doi.org/10.1007/s10838-021-09590-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 AR 54 2022 3 07 10 433-450 |
| allfieldsGer |
10.1007/s10838-021-09590-2 doi (DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p DE-627 ger DE-627 rakwb eng 000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Ortner, Ronald verfasserin (orcid)0000-0001-6033-2208 aut Adaptive Algorithms for Meta-Induction 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. Online learning Regret Prediction with expert advice Multi-armed bandit problem Enthalten in Journal for general philosophy of science Springer Netherlands, 1990 54(2022), 3 vom: 07. Okt., Seite 433-450 (DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 0925-4560 nnns volume:54 year:2022 number:3 day:07 month:10 pages:433-450 https://doi.org/10.1007/s10838-021-09590-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 AR 54 2022 3 07 10 433-450 |
| allfieldsSound |
10.1007/s10838-021-09590-2 doi (DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p DE-627 ger DE-627 rakwb eng 000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Ortner, Ronald verfasserin (orcid)0000-0001-6033-2208 aut Adaptive Algorithms for Meta-Induction 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2022 Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. Online learning Regret Prediction with expert advice Multi-armed bandit problem Enthalten in Journal for general philosophy of science Springer Netherlands, 1990 54(2022), 3 vom: 07. Okt., Seite 433-450 (DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 0925-4560 nnns volume:54 year:2022 number:3 day:07 month:10 pages:433-450 https://doi.org/10.1007/s10838-021-09590-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 AR 54 2022 3 07 10 433-450 |
| language |
English |
| source |
Enthalten in Journal for general philosophy of science 54(2022), 3 vom: 07. Okt., Seite 433-450 volume:54 year:2022 number:3 day:07 month:10 pages:433-450 |
| sourceStr |
Enthalten in Journal for general philosophy of science 54(2022), 3 vom: 07. Okt., Seite 433-450 volume:54 year:2022 number:3 day:07 month:10 pages:433-450 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Online learning Regret Prediction with expert advice Multi-armed bandit problem |
| dewey-raw |
000 |
| isfreeaccess_bool |
false |
| container_title |
Journal for general philosophy of science |
| authorswithroles_txt_mv |
Ortner, Ronald @@aut@@ |
| publishDateDaySort_date |
2022-10-07T00:00:00Z |
| hierarchy_top_id |
130910597 |
| dewey-sort |
0 |
| id |
OLC2145645810 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2145645810</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118105845.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10838-021-09590-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2145645810</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10838-021-09590-2-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">000</subfield><subfield code="a">500</subfield><subfield code="a">100</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">050</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">19,2</subfield><subfield code="a">24</subfield><subfield code="a">5,1</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">LING</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ortner, Ronald</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6033-2208</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Adaptive Algorithms for Meta-Induction</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">© The Author(s) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Online learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regret</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prediction with expert advice</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-armed bandit problem</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal for general philosophy of science</subfield><subfield code="d">Springer Netherlands, 1990</subfield><subfield code="g">54(2022), 3 vom: 07. Okt., Seite 433-450</subfield><subfield code="w">(DE-627)130910597</subfield><subfield code="w">(DE-600)1048887-X</subfield><subfield code="w">(DE-576)025001191</subfield><subfield code="x">0925-4560</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:54</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:3</subfield><subfield code="g">day:07</subfield><subfield code="g">month:10</subfield><subfield code="g">pages:433-450</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10838-021-09590-2</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">FID-LING</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-BBI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_50</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4318</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4385</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">54</subfield><subfield code="j">2022</subfield><subfield code="e">3</subfield><subfield code="b">07</subfield><subfield code="c">10</subfield><subfield code="h">433-450</subfield></datafield></record></collection>
|
| author |
Ortner, Ronald |
| spellingShingle |
Ortner, Ronald ddc 000 ddc 050 ssgn 19,2 fid LING misc Online learning misc Regret misc Prediction with expert advice misc Multi-armed bandit problem Adaptive Algorithms for Meta-Induction |
| authorStr |
Ortner, Ronald |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)130910597 |
| format |
Article |
| dewey-ones |
000 - Computer science, information & general works 500 - Natural sciences & mathematics 100 - Philosophy & psychology 050 - General serial publications |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0925-4560 |
| topic_title |
000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid Adaptive Algorithms for Meta-Induction Online learning Regret Prediction with expert advice Multi-armed bandit problem |
| topic |
ddc 000 ddc 050 ssgn 19,2 fid LING misc Online learning misc Regret misc Prediction with expert advice misc Multi-armed bandit problem |
| topic_unstemmed |
ddc 000 ddc 050 ssgn 19,2 fid LING misc Online learning misc Regret misc Prediction with expert advice misc Multi-armed bandit problem |
| topic_browse |
ddc 000 ddc 050 ssgn 19,2 fid LING misc Online learning misc Regret misc Prediction with expert advice misc Multi-armed bandit problem |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Journal for general philosophy of science |
| hierarchy_parent_id |
130910597 |
| dewey-tens |
000 - Computer science, knowledge & systems 500 - Science 100 - Philosophy 050 - Magazines, journals & serials |
| hierarchy_top_title |
Journal for general philosophy of science |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)130910597 (DE-600)1048887-X (DE-576)025001191 |
| title |
Adaptive Algorithms for Meta-Induction |
| ctrlnum |
(DE-627)OLC2145645810 (DE-He213)s10838-021-09590-2-p |
| title_full |
Adaptive Algorithms for Meta-Induction |
| author_sort |
Ortner, Ronald |
| journal |
Journal for general philosophy of science |
| journalStr |
Journal for general philosophy of science |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works 500 - Science 100 - Philosophy & psychology |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
433 |
| author_browse |
Ortner, Ronald |
| container_volume |
54 |
| class |
000 500 100 VZ 050 VZ 19,2 24 5,1 ssgn LING DE-30 fid |
| format_se |
Aufsätze |
| author-letter |
Ortner, Ronald |
| doi_str_mv |
10.1007/s10838-021-09590-2 |
| normlink |
(ORCID)0000-0001-6033-2208 |
| normlink_prefix_str_mv |
(orcid)0000-0001-6033-2208 |
| dewey-full |
000 500 100 050 |
| title_sort |
adaptive algorithms for meta-induction |
| title_auth |
Adaptive Algorithms for Meta-Induction |
| abstract |
Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. © The Author(s) 2022 |
| abstractGer |
Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. © The Author(s) 2022 |
| abstract_unstemmed |
Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner. © The Author(s) 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC FID-LING SSG-OLC-PHI SSG-OPC-BBI GBV_ILN_22 GBV_ILN_50 GBV_ILN_171 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4318 GBV_ILN_4385 |
| container_issue |
3 |
| title_short |
Adaptive Algorithms for Meta-Induction |
| url |
https://doi.org/10.1007/s10838-021-09590-2 |
| remote_bool |
false |
| ppnlink |
130910597 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s10838-021-09590-2 |
| up_date |
2024-07-04T03:54:03.900Z |
| _version_ |
1803619133189783552 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2145645810</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240118105845.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">240118s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10838-021-09590-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2145645810</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10838-021-09590-2-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">000</subfield><subfield code="a">500</subfield><subfield code="a">100</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">050</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">19,2</subfield><subfield code="a">24</subfield><subfield code="a">5,1</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">LING</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ortner, Ronald</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6033-2208</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Adaptive Algorithms for Meta-Induction</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">© The Author(s) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Work in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Online learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regret</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prediction with expert advice</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-armed bandit problem</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal for general philosophy of science</subfield><subfield code="d">Springer Netherlands, 1990</subfield><subfield code="g">54(2022), 3 vom: 07. Okt., Seite 433-450</subfield><subfield code="w">(DE-627)130910597</subfield><subfield code="w">(DE-600)1048887-X</subfield><subfield code="w">(DE-576)025001191</subfield><subfield code="x">0925-4560</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:54</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:3</subfield><subfield code="g">day:07</subfield><subfield code="g">month:10</subfield><subfield code="g">pages:433-450</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10838-021-09590-2</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">FID-LING</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-BBI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_50</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4318</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4385</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">54</subfield><subfield code="j">2022</subfield><subfield code="e">3</subfield><subfield code="b">07</subfield><subfield code="c">10</subfield><subfield code="h">433-450</subfield></datafield></record></collection>
|
| score |
7.3997 |