Course ObjectiveStudents who pass this course succesfully, (i) can devlelop learning
and optimization algorithms in a stochastic environment, (ii) are able
to mathemtically analyze the properties of learning and optimization
alogirthms, and (iii) can perfom an optimziaton study and report on
Course ContentThis is course on advanced simulation techniques. The methodological
part of the course focusses on the theory of recursive learning and
optimization algorithms known as stochastic approximation.
Topics coverd in this course are, among others, machine learning in a
stochastic environment, design of learning algorithms from ODEs, and
gradient estimation algorithms.
Teaching MethodsCombined lectures and tutorials
Method of AssessmentFinal exam – Individual assessment
Individual assignment - Individual assessment
Entry RequirementsAnalysis, basic probability theory, stochastic processes, basic
LiteratureHandout of monograph “Gradient based Stochastic Optimization”, F.
Vásquez-Abad and B. Heidergott, 2017.
Target AudienceThe course is suitable to be taken in an exchange program
Additional InformationIn presence of uncertainty, gradients typically fail to be available in
analytical form and optimization has to resort to simulation-based
algorithms. Unbiased gradient estimators are a main ingredient in
simulation-based optimization methods. The focus of this course is on
unbiased gradient estimators and their application in stochastic
simulation-based optimization and learning algorithms. Next to classical
stochastic gradient methods, this course also covers a range of related
topics such as model and parameter insecurity, robust optimization and
sample average approximation. Applications will stem from a wide range
of domains from Financial Engineering over Inventory Management to
Waiting Time Minimization.
|Language of Tuition||English|
|Faculty||School of Business and Economics|
|Course Coordinator||prof. dr. B.F. Heidergott|
|Examiner||prof. dr. B.F. Heidergott|
You need to register for this course yourself
Last-minute registration is available for this course.
|Teaching Methods||Seminar, Lecture|
This course is also available as: