Group online adaptive learning
Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-ad...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Zweig, Alon [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2017 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s) 2017 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Machine learning - Springer US, 1986, 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 |
|---|---|
| Übergeordnetes Werk: |
volume:106 ; year:2017 ; number:9-10 ; day:01 ; month:08 ; pages:1747-1770 |
| Links: |
|---|
| DOI / URN: |
10.1007/s10994-017-5661-5 |
|---|
| Katalog-ID: |
OLC2026527407 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2026527407 | ||
| 003 | DE-627 | ||
| 005 | 20230503172307.0 | ||
| 007 | tu | ||
| 008 | 200820s2017 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10994-017-5661-5 |2 doi | |
| 035 | |a (DE-627)OLC2026527407 | ||
| 035 | |a (DE-He213)s10994-017-5661-5-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 150 |a 004 |q VZ |
| 100 | 1 | |a Zweig, Alon |e verfasserin |0 (orcid)0000-0003-3797-1591 |4 aut | |
| 245 | 1 | 0 | |a Group online adaptive learning |
| 264 | 1 | |c 2017 | |
| 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) 2017 | ||
| 520 | |a Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. | ||
| 650 | 4 | |a Multi-task learning | |
| 650 | 4 | |a Knowledge transfer | |
| 650 | 4 | |a Adaptive learning | |
| 650 | 4 | |a Online learning | |
| 650 | 4 | |a Domain adaptation | |
| 700 | 1 | |a Chechik, Gal |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Machine learning |d Springer US, 1986 |g 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 |w (DE-627)12920403X |w (DE-600)54638-0 |w (DE-576)014457377 |x 0885-6125 |7 nnns |
| 773 | 1 | 8 | |g volume:106 |g year:2017 |g number:9-10 |g day:01 |g month:08 |g pages:1747-1770 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s10994-017-5661-5 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_4012 | ||
| 912 | |a GBV_ILN_4046 | ||
| 912 | |a GBV_ILN_4318 | ||
| 951 | |a AR | ||
| 952 | |d 106 |j 2017 |e 9-10 |b 01 |c 08 |h 1747-1770 | ||
| author_variant |
a z az g c gc |
|---|---|
| matchkey_str |
article:08856125:2017----::ruolnaatv |
| hierarchy_sort_str |
2017 |
| publishDate |
2017 |
| allfields |
10.1007/s10994-017-5661-5 doi (DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p DE-627 ger DE-627 rakwb eng 150 004 VZ Zweig, Alon verfasserin (orcid)0000-0003-3797-1591 aut Group online adaptive learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2017 Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation Chechik, Gal aut Enthalten in Machine learning Springer US, 1986 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 (DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 0885-6125 nnns volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 https://doi.org/10.1007/s10994-017-5661-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 AR 106 2017 9-10 01 08 1747-1770 |
| spelling |
10.1007/s10994-017-5661-5 doi (DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p DE-627 ger DE-627 rakwb eng 150 004 VZ Zweig, Alon verfasserin (orcid)0000-0003-3797-1591 aut Group online adaptive learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2017 Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation Chechik, Gal aut Enthalten in Machine learning Springer US, 1986 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 (DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 0885-6125 nnns volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 https://doi.org/10.1007/s10994-017-5661-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 AR 106 2017 9-10 01 08 1747-1770 |
| allfields_unstemmed |
10.1007/s10994-017-5661-5 doi (DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p DE-627 ger DE-627 rakwb eng 150 004 VZ Zweig, Alon verfasserin (orcid)0000-0003-3797-1591 aut Group online adaptive learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2017 Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation Chechik, Gal aut Enthalten in Machine learning Springer US, 1986 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 (DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 0885-6125 nnns volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 https://doi.org/10.1007/s10994-017-5661-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 AR 106 2017 9-10 01 08 1747-1770 |
| allfieldsGer |
10.1007/s10994-017-5661-5 doi (DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p DE-627 ger DE-627 rakwb eng 150 004 VZ Zweig, Alon verfasserin (orcid)0000-0003-3797-1591 aut Group online adaptive learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2017 Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation Chechik, Gal aut Enthalten in Machine learning Springer US, 1986 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 (DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 0885-6125 nnns volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 https://doi.org/10.1007/s10994-017-5661-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 AR 106 2017 9-10 01 08 1747-1770 |
| allfieldsSound |
10.1007/s10994-017-5661-5 doi (DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p DE-627 ger DE-627 rakwb eng 150 004 VZ Zweig, Alon verfasserin (orcid)0000-0003-3797-1591 aut Group online adaptive learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2017 Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation Chechik, Gal aut Enthalten in Machine learning Springer US, 1986 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 (DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 0885-6125 nnns volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 https://doi.org/10.1007/s10994-017-5661-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 AR 106 2017 9-10 01 08 1747-1770 |
| language |
English |
| source |
Enthalten in Machine learning 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 |
| sourceStr |
Enthalten in Machine learning 106(2017), 9-10 vom: 01. Aug., Seite 1747-1770 volume:106 year:2017 number:9-10 day:01 month:08 pages:1747-1770 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation |
| dewey-raw |
150 |
| isfreeaccess_bool |
false |
| container_title |
Machine learning |
| authorswithroles_txt_mv |
Zweig, Alon @@aut@@ Chechik, Gal @@aut@@ |
| publishDateDaySort_date |
2017-08-01T00:00:00Z |
| hierarchy_top_id |
12920403X |
| dewey-sort |
3150 |
| id |
OLC2026527407 |
| 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">OLC2026527407</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230503172307.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10994-017-5661-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2026527407</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10994-017-5661-5-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">150</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zweig, Alon</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-3797-1591</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Group online adaptive learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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) 2017</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-task learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge transfer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Adaptive learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Online learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Domain adaptation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chechik, Gal</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Machine learning</subfield><subfield code="d">Springer US, 1986</subfield><subfield code="g">106(2017), 9-10 vom: 01. Aug., Seite 1747-1770</subfield><subfield code="w">(DE-627)12920403X</subfield><subfield code="w">(DE-600)54638-0</subfield><subfield code="w">(DE-576)014457377</subfield><subfield code="x">0885-6125</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:106</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:9-10</subfield><subfield code="g">day:01</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:1747-1770</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10994-017-5661-5</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">GBV_ILN_24</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4318</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">106</subfield><subfield code="j">2017</subfield><subfield code="e">9-10</subfield><subfield code="b">01</subfield><subfield code="c">08</subfield><subfield code="h">1747-1770</subfield></datafield></record></collection>
|
| author |
Zweig, Alon |
| spellingShingle |
Zweig, Alon ddc 150 misc Multi-task learning misc Knowledge transfer misc Adaptive learning misc Online learning misc Domain adaptation Group online adaptive learning |
| authorStr |
Zweig, Alon |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)12920403X |
| format |
Article |
| dewey-ones |
150 - Psychology 004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0885-6125 |
| topic_title |
150 004 VZ Group online adaptive learning Multi-task learning Knowledge transfer Adaptive learning Online learning Domain adaptation |
| topic |
ddc 150 misc Multi-task learning misc Knowledge transfer misc Adaptive learning misc Online learning misc Domain adaptation |
| topic_unstemmed |
ddc 150 misc Multi-task learning misc Knowledge transfer misc Adaptive learning misc Online learning misc Domain adaptation |
| topic_browse |
ddc 150 misc Multi-task learning misc Knowledge transfer misc Adaptive learning misc Online learning misc Domain adaptation |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Machine learning |
| hierarchy_parent_id |
12920403X |
| dewey-tens |
150 - Psychology 000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Machine learning |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)12920403X (DE-600)54638-0 (DE-576)014457377 |
| title |
Group online adaptive learning |
| ctrlnum |
(DE-627)OLC2026527407 (DE-He213)s10994-017-5661-5-p |
| title_full |
Group online adaptive learning |
| author_sort |
Zweig, Alon |
| journal |
Machine learning |
| journalStr |
Machine learning |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
100 - Philosophy & psychology 000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2017 |
| contenttype_str_mv |
txt |
| container_start_page |
1747 |
| author_browse |
Zweig, Alon Chechik, Gal |
| container_volume |
106 |
| class |
150 004 VZ |
| format_se |
Aufsätze |
| author-letter |
Zweig, Alon |
| doi_str_mv |
10.1007/s10994-017-5661-5 |
| normlink |
(ORCID)0000-0003-3797-1591 |
| normlink_prefix_str_mv |
(orcid)0000-0003-3797-1591 |
| dewey-full |
150 004 |
| title_sort |
group online adaptive learning |
| title_auth |
Group online adaptive learning |
| abstract |
Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. © The Author(s) 2017 |
| abstractGer |
Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. © The Author(s) 2017 |
| abstract_unstemmed |
Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments. © The Author(s) 2017 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_70 GBV_ILN_4012 GBV_ILN_4046 GBV_ILN_4318 |
| container_issue |
9-10 |
| title_short |
Group online adaptive learning |
| url |
https://doi.org/10.1007/s10994-017-5661-5 |
| remote_bool |
false |
| author2 |
Chechik, Gal |
| author2Str |
Chechik, Gal |
| ppnlink |
12920403X |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s10994-017-5661-5 |
| up_date |
2024-07-04T04:10:13.487Z |
| _version_ |
1803620149874393088 |
| 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">OLC2026527407</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230503172307.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10994-017-5661-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2026527407</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10994-017-5661-5-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">150</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zweig, Alon</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-3797-1591</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Group online adaptive learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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) 2017</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-task learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge transfer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Adaptive learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Online learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Domain adaptation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chechik, Gal</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Machine learning</subfield><subfield code="d">Springer US, 1986</subfield><subfield code="g">106(2017), 9-10 vom: 01. Aug., Seite 1747-1770</subfield><subfield code="w">(DE-627)12920403X</subfield><subfield code="w">(DE-600)54638-0</subfield><subfield code="w">(DE-576)014457377</subfield><subfield code="x">0885-6125</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:106</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:9-10</subfield><subfield code="g">day:01</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:1747-1770</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10994-017-5661-5</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">GBV_ILN_24</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4318</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">106</subfield><subfield code="j">2017</subfield><subfield code="e">9-10</subfield><subfield code="b">01</subfield><subfield code="c">08</subfield><subfield code="h">1747-1770</subfield></datafield></record></collection>
|
| score |
7.400296 |