Staff View
Stochastic dilemmas

Descriptive

TitleInfo
Title
Stochastic dilemmas
SubTitle
foundations and applications
Name (type = personal)
NamePart (type = family)
Goschin
NamePart (type = given)
Sergiu
NamePart (type = date)
1980-
DisplayForm
Sergiu Goschin
Role
RoleTerm (authority = RULIB)
author
Name (type = personal)
NamePart (type = family)
Littman
NamePart (type = given)
Michael L
DisplayForm
Michael L Littman
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
chair
Name (type = personal)
NamePart (type = family)
Hirsh
NamePart (type = given)
Haym
DisplayForm
Haym Hirsh
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
co-chair
Name (type = personal)
NamePart (type = family)
Kopparty
NamePart (type = given)
Swastik
DisplayForm
Swastik Kopparty
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
internal member
Name (type = personal)
NamePart (type = family)
Mannor
NamePart (type = given)
Shie
DisplayForm
Shie Mannor
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
outside member
Name (type = corporate)
NamePart
Rutgers University
Role
RoleTerm (authority = RULIB)
degree grantor
Name (type = corporate)
NamePart
Graduate School - New Brunswick
Role
RoleTerm (authority = RULIB)
school
TypeOfResource
Text
Genre (authority = marcgt)
theses
OriginInfo
DateCreated (qualifier = exact)
2014
DateOther (qualifier = exact); (type = degree)
2014-05
Place
PlaceTerm (type = code)
xx
Language
LanguageTerm (authority = ISO639-2b); (type = code)
eng
Abstract (type = abstract)
One of the significant challenges when solving optimization problems is addressing possible inaccurate or inconsistent function evaluations. Surprisingly and interestingly, this problem is far from trivial even in one of the most basic possible settings: evaluating which of two options is better when the values of the two options are random variables (a stochastic dilemma). Problems in this space have often been studied in the statistics, operations research and computer-science communities under the name of "multi-armed bandits". While most of the previous work has focused on dealing with noise in an online setting, in this dissertation, I will focus on offline optimization where the goal is to return a reasonable solution with high probability using a finite number of samples. I will discuss a set of problem settings of increasing complexity that allow one to derive formal algorithmic bounds. I will point to and discuss interesting connections between stochastic optimization and noisy data annotation, a problem where the goal is to identify the label of an object from a series of noisy evaluations. As a first contribution, I will introduce and formally analyze a set of novel algorithms that improve the state of the art and provide new insights for solving the stochastic optimization and noisy data-annotation problems. I will then formally prove a novel result: That a widely used derivative-free optimization algorithm (the cross-entropy method) is optimizing for quantiles instead of expectation in stochastic optimization settings. I will back up the theoretical claims on the optimization side with experimental results in a set of non-trivial planning and reinforcement-learning domains. Finally, I will discuss the application of the above algorithms for solving noisy data-annotation problems in a setting involving real crowdsourcing experiments.
Subject (authority = RUETD)
Topic
Computer Science
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Identifier (type = RULIB)
ETD
Identifier
ETD_5428
PhysicalDescription
Form (authority = gmd)
electronic resource
InternetMediaType
application/pdf
InternetMediaType
text/xml
Extent
xv, 188 p. : ill.
Note (type = degree)
Ph.D.
Note (type = bibliography)
Includes bibliographical references
Note (type = statement of responsibility)
by Sergiu Goschin
Subject (authority = ETD-LCSH)
Topic
Stochastic processes
Subject (authority = ETD-LCSH)
Topic
Stochastic analysis
RelatedItem (type = host)
TitleInfo
Title
Graduate School - New Brunswick Electronic Theses and Dissertations
Identifier (type = local)
rucore19991600001
Location
PhysicalLocation (authority = marcorg); (displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier (type = doi)
doi:10.7282/T3H993GS
Genre (authority = ExL-Esploro)
ETD doctoral
Back to the top

Rights

RightsDeclaration (ID = rulibRdec0006)
The author owns the copyright to this work.
RightsHolder (type = personal)
Name
FamilyName
Goschin
GivenName
Sergiu
Role
Copyright Holder
RightsEvent
Type
Permission or license
DateTime (encoding = w3cdtf); (qualifier = exact); (point = start)
2014-04-10 04:45:02
AssociatedEntity
Name
Sergiu Goschin
Role
Copyright holder
Affiliation
Rutgers University. Graduate School - New Brunswick
AssociatedObject
Type
License
Name
Author Agreement License
Detail
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.
Copyright
Status
Copyright protected
Availability
Status
Open
Reason
Permission or license
Back to the top

Technical

RULTechMD (ID = TECHNICAL1)
ContentModel
ETD
OperatingSystem (VERSION = 5.1)
windows xp
Back to the top
Version 8.3.13
Rutgers University Libraries - Copyright ©2021