Teaching and Learning in Uncertainty

We investigate a simple model for social learning with two agents: a teacher and a student. The teacher's goal is to teach the student the state of the world; however, the teacher himself is not certain about the state of the world and needs to simultaneously learn this parameter and teach it t...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on information theory Vol. 67; no. 1; pp. 598 - 615
Main Authors Jog, Varun, Loh, Po-Ling
Format Journal Article
LanguageEnglish
Published New York IEEE 01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text

Cover

Loading…
Abstract We investigate a simple model for social learning with two agents: a teacher and a student. The teacher's goal is to teach the student the state of the world; however, the teacher himself is not certain about the state of the world and needs to simultaneously learn this parameter and teach it to the student. We model the teacher's and student's uncertainties via noisy transmission channels, and employ two simple decoding strategies for the student. We focus on two teaching strategies: a "low-effort" strategy of simply forwarding information, and a "high-effort" strategy of communicating the teacher's current best estimate of the world at each time instant, based on his own cumulative learning. Using tools from large deviation theory, we calculate the exact learning rates for these strategies and demonstrate regimes where the low-effort strategy outperforms the high-effort strategy. Finally, we present a conjecture concerning the optimal learning rate for the student over all joint strategies between the student and the teacher.
AbstractList We investigate a simple model for social learning with two agents: a teacher and a student. The teacher’s goal is to teach the student the state of the world; however, the teacher himself is not certain about the state of the world and needs to simultaneously learn this parameter and teach it to the student. We model the teacher’s and student’s uncertainties via noisy transmission channels, and employ two simple decoding strategies for the student. We focus on two teaching strategies: a “low-effort” strategy of simply forwarding information, and a “high-effort” strategy of communicating the teacher’s current best estimate of the world at each time instant, based on his own cumulative learning. Using tools from large deviation theory, we calculate the exact learning rates for these strategies and demonstrate regimes where the low-effort strategy outperforms the high-effort strategy. Finally, we present a conjecture concerning the optimal learning rate for the student over all joint strategies between the student and the teacher.
Author Loh, Po-Ling
Jog, Varun
Author_xml – sequence: 1
  givenname: Varun
  orcidid: 0000-0003-4159-0900
  surname: Jog
  fullname: Jog, Varun
  email: vjog@wisc.edu
  organization: Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USA
– sequence: 2
  givenname: Po-Ling
  orcidid: 0000-0002-6514-7834
  surname: Loh
  fullname: Loh, Po-Ling
  email: ploh@stat.wisc.edu
  organization: Department of Statistics, University of Wisconsin-Madison, Madison, WI, USA
BookMark eNo9kE1LAzEQhoNUsK3eBS8Fve46mcxuk6MUq4WCl-05pNlZ3aLZmt0e-u9NafE0vMz7Ac9EjEIXWIh7CbmUYJ6rVZUjIOQKFGjCKzGWRTHPTFnQSIwBpM4Mkb4Rk77fJUmFxLF4qtj5rzZ8zlyoZ2t2MZxEG2ab4DkOrg3D8VZcN-6757vLnYrN8rVavGfrj7fV4mWdeTRyyNi7LfkGS2hcvUUlAWsyhSsV1B7I6KbWRLJhpefKG2nKmiR6LiVvmRHUVDyee_ex-z1wP9hdd4ghTVqkeSrUqCi54Ozysev7yI3dx_bHxaOVYE8sbGJhTyzshUWKPJwjLTP_2w0ipr_6A3nbWkA
CODEN IETTAW
CitedBy_id crossref_primary_10_1109_TIT_2023_3292356
crossref_primary_10_1109_TIT_2023_3247829
crossref_primary_10_1109_TIT_2023_3335933
crossref_primary_10_1109_TIT_2021_3107733
crossref_primary_10_2478_amns_2023_2_00516
crossref_primary_10_1109_TIT_2023_3283802
crossref_primary_10_1109_TIT_2022_3180001
Cites_doi 10.1137/0306011
10.2307/1426252
10.1007/s00440-013-0479-y
10.1007/978-3-540-77200-2_1
10.1016/0022-0531(82)90099-0
10.2307/2298060
10.1214/14-PS230
10.1109/JSAC.2013.130412
10.1109/ISIT.2019.8849298
10.1086/261849
10.1111/1467-937X.00059
10.1016/S0899-8256(03)00144-1
10.2139/ssrn.2266979
10.1017/9781108591034
10.1093/qje/qjaa026
10.1146/annurev-economics-120213-012609
10.2307/2285509
10.2307/2118364
10.1109/PROC.1980.11718
10.1111/1468-0262.00113
10.1214/aos/1176343654
10.1017/CBO9781139871495
10.1086/261890
10.1073/pnas.35.10.605
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TIT.2020.3030842
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library Online
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Education
Computer Science
EISSN 1557-9654
EndPage 615
ExternalDocumentID 10_1109_TIT_2020_3030842
9222308
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: CCF-1841190
  funderid: 10.13039/100000001
– fundername: NSF
  grantid: DMS-1749857
  funderid: 10.13039/100000001
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AASAJ
AAYOK
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACGOD
ACIWK
AENEX
AETEA
AETIX
AI.
AIBXA
AKJIK
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RIG
RNS
RXW
TAE
TN5
VH1
VJK
XFK
AAYXX
AGSQL
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-ecab4cf260fadb23102d495a630dc0498fd8441fe3873c9196d412ce61ebee203
IEDL.DBID RIE
ISSN 0018-9448
IngestDate Thu Oct 10 17:59:03 EDT 2024
Fri Dec 06 01:26:01 EST 2024
Wed Jun 26 19:26:24 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-ecab4cf260fadb23102d495a630dc0498fd8441fe3873c9196d412ce61ebee203
ORCID 0000-0003-4159-0900
0000-0002-6514-7834
PQID 2472318234
PQPubID 36024
PageCount 18
ParticipantIDs ieee_primary_9222308
proquest_journals_2472318234
crossref_primary_10_1109_TIT_2020_3030842
PublicationCentury 2000
PublicationDate 2021-Jan.
2021-1-00
20210101
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – month: 01
  year: 2021
  text: 2021-Jan.
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on information theory
PublicationTitleAbbrev TIT
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
ref30
ref11
ref10
ref2
ref17
ref16
molavi (ref5) 2017
chamley (ref1) 2004
haz?a (ref19) 0
zhu (ref32) 2015
lévy (ref27) 1940; 7
ref24
ref23
ref25
ref20
ref22
amin rahimian (ref18) 2016
ref28
ref29
ref8
ref7
ref9
ref4
ref3
andersen (ref26) 1955; 2
ref6
dupuis (ref31) 2011; 902
ho (ref21) 1980; 68
References_xml – ident: ref22
  doi: 10.1137/0306011
– ident: ref23
  doi: 10.2307/1426252
– ident: ref14
  doi: 10.1007/s00440-013-0479-y
– year: 2004
  ident: ref1
  publication-title: Rational Herds Economic Models of Social Learning
  contributor:
    fullname: chamley
– ident: ref24
  doi: 10.1007/978-3-540-77200-2_1
– ident: ref9
  doi: 10.1016/0022-0531(82)90099-0
– ident: ref3
  doi: 10.2307/2298060
– year: 2017
  ident: ref5
  article-title: Foundations of non-Bayesian social learning
  contributor:
    fullname: molavi
– ident: ref2
  doi: 10.1214/14-PS230
– ident: ref20
  doi: 10.1109/JSAC.2013.130412
– volume: 7
  start-page: 283
  year: 1940
  ident: ref27
  article-title: Sur certains processus stochastiques homogènes
  publication-title: Compositio Math
  contributor:
    fullname: lévy
– ident: ref29
  doi: 10.1109/ISIT.2019.8849298
– ident: ref11
  doi: 10.1086/261849
– ident: ref17
  doi: 10.1111/1467-937X.00059
– volume: 902
  year: 2011
  ident: ref31
  publication-title: A Weak Convergence Approach to the Theory of Large Deviations
  contributor:
    fullname: dupuis
– ident: ref13
  doi: 10.1016/S0899-8256(03)00144-1
– ident: ref4
  doi: 10.2139/ssrn.2266979
– year: 0
  ident: ref19
  article-title: Bayesian decision making in groups is hard
  publication-title: Oper Res
  contributor:
    fullname: haz?a
– ident: ref28
  doi: 10.1017/9781108591034
– volume: 2
  start-page: 195
  year: 1955
  ident: ref26
  article-title: On the fluctuations of sums of random variables II
  publication-title: Math Scandinavica
  contributor:
    fullname: andersen
– ident: ref6
  doi: 10.1093/qje/qjaa026
– ident: ref7
  doi: 10.1146/annurev-economics-120213-012609
– ident: ref15
  doi: 10.2307/2285509
– ident: ref10
  doi: 10.2307/2118364
– volume: 68
  start-page: 644
  year: 1980
  ident: ref21
  article-title: Team decision theory and information structures
  publication-title: Proc IEEE
  doi: 10.1109/PROC.1980.11718
  contributor:
    fullname: ho
– ident: ref12
  doi: 10.1111/1468-0262.00113
– ident: ref8
  doi: 10.1214/aos/1176343654
– ident: ref30
  doi: 10.1017/CBO9781139871495
– start-page: 4083
  year: 2015
  ident: ref32
  article-title: Machine teaching: An inverse problem to machine learning and an approach toward optimal education
  publication-title: Proc 29th AAAI Conf Artif Intell
  contributor:
    fullname: zhu
– year: 2016
  ident: ref18
  article-title: Bayesian heuristics for group decisions
  publication-title: arXiv 1611 01006
  contributor:
    fullname: amin rahimian
– ident: ref16
  doi: 10.1086/261890
– ident: ref25
  doi: 10.1073/pnas.35.10.605
SSID ssj0014512
Score 2.475062
Snippet We investigate a simple model for social learning with two agents: a teacher and a student. The teacher's goal is to teach the student the state of the world;...
We investigate a simple model for social learning with two agents: a teacher and a student. The teacher’s goal is to teach the student the state of the world;...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Publisher
StartPage 598
SubjectTerms Analytical models
Communication
Computational modeling
Decoding
Education
Large deviations theory
Learning
Mathematical model
Noise measurement
Random variables
random walks
social learning
Strategy
Teachers
Teaching
Uncertainty
Title Teaching and Learning in Uncertainty
URI https://ieeexplore.ieee.org/document/9222308
https://www.proquest.com/docview/2472318234
Volume 67
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwED2VTjBQaEEUCsrQBYm08cVO4hEhqoJUplTqFiW2gxBSiiAd4NdjO07F18CWIZZOPp_vnu_dHcBYcCLKHIkfKsx9ypjJ78rQp0SgKBUyaQuFFw_RfEnvV2zVgattLYxSypLP1MR82ly-XIuNeSqbcuPMTGXvTsyjplZrmzGgjDSdwYk2YI052pRkwKfpXaqBIGp8apqzUPzmguxMlV8XsfUusx4sWrkaUsnzZFMXE_Hxo2XjfwU_gH0XZnrXzbk4hI6q-tBrRzh4zqL7ZmizI3j0Ye9Lb8IBjFPHs_TySnquDeuj91R5S73S8gjq9yNYzm7Tm7nvRir4AjmpfSXygopSg5gyl4WJ7VBqiJRHYSCFBgtJKRMdIJUqTOJQ65FHkhIUKiJa2QqD8Bi61bpSJ-CxELlEDbiKWNAcWWEcnSwLboipQrEhXLa7nL00nTMyizgCnmmNZEYjmdPIEAZm07b_uf0awqhVS-ZM6y1DGmu5Ewzp6d-rzmAXDfHEvpOMoFu_btS5jhzq4sIemU-Blr16
link.rule.ids 314,780,784,796,27924,27925,54758
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED5VMAADhRZEoUCGLkikjV9pPCJE1ULbKZW6RYntIISUIkgH-PXYjlPxGtgyxNLJ5_Pd5_vuDqAnOBJ5ipFPFE59ypjJ70riUySwyBVm0hYKz-bheEHvl2zZgOtNLYxSypLPVN982ly-XIm1eSobcOPMTGXvNqM6zq2qtTY5A8pQ1RscaRPWqKNOSgZ8EE9iDQWxRqimPQvF35yQnary6yq2_mXUhFktWUUree6vy6wvPn40bfyv6Aew7wJN76Y6GYfQUEULmvUQB8_ZdMuMbXYUjxbsfelO2IZe7JiWXlpIzzViffSeCm-hV1omQfl-BIvRXXw79t1QBV9gjkpfiTSjItcwJk9lZqI7LDVISkMSSKHhQpTLSIdIuSLRkGhN8lBShIUKkVa3wgE5hq1iVagT8BjBXGINubKhoClmmXF1Ms-4oaYKxTpwVe9y8lL1zkgs5gh4ojWSGI0kTiMdaJtN2_zn9qsD3VotiTOutwTToZY7woSe_r3qEnbG8WyaTCfzhzPYxYaGYl9NurBVvq7VuY4jyuzCHp9PrXLAzQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Teaching+and+Learning+in+Uncertainty&rft.jtitle=IEEE+transactions+on+information+theory&rft.au=Jog%2C+Varun&rft.au=Loh%2C+Po-Ling&rft.date=2021-01-01&rft.issn=0018-9448&rft.eissn=1557-9654&rft.volume=67&rft.issue=1&rft.spage=598&rft.epage=615&rft_id=info:doi/10.1109%2FTIT.2020.3030842&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIT_2020_3030842
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9448&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9448&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9448&client=summon