Title	Model Uncertainty and Robust Stochastic Modeling
Creator	Lam, Henry
Publisher	Banff International Research Station for Mathematical Innovation and Discovery
Date Issued	2015-06-01T13:38
Description	Virtually any performance analysis in stochastic modeling relies on input model assumptions that, to some extent, deviate from the truth. This talk will investigate a worst-case framework to quantify these model errors and correspondingly robustify the stochastic outputs. It entails posting optimization programs over the input probability distributions, with constraints representing the modeler’s partial, nonparametric knowledge about them. We illustrate these optimization formulations in several contexts in stochastic modeling, describe their computational challenges, and present some machinery in approximating their solutions.
Extent	55 minutes
Subject	Mathematics; Probability theory and stochastic processes; Statistics; Operation research
Type	Moving Image
File Format	video/mp4
Language	eng
Notes	Author affiliation: University of Michigan
Series	BIRS Workshop Lecture Videos (Banff, Alta)
Date Available	2016-01-04
Provider	Vancouver : University of British Columbia Library
Rights	Attribution-NonCommercial-NoDerivs 2.5 Canada
DOI	10.14288/1.0223074
URI	http://hdl.handle.net/2429/56145
Affiliation	Non UBC
Peer Review Status	Unreviewed
Scholarly Level	Faculty
Rights URI	http://creativecommons.org/licenses/by-nc-nd/2.5/ca/
Aggregated Source Repository	DSpace

Open Collections

BIRS Workshop Lecture Videos