Title	From Data to Decisions: Distributionally Robust Optimization is Optimal
Creator	Kuhn, Daniel
Publisher	Banff International Research Station for Mathematical Innovation and Discovery
Date Issued	2018-03-09T10:33
Description	Data-driven stochastic programming aims to find a procedure that transforms time series data to a near-optimal decision (a prescriptor) and to a prediction of this decision's expected cost under the unknown data-generating distribution (a predictor). We propose a meta-optimization problem to find the least conservative predictors and prescriptors subject to constraints on their out-of-sample disappointment. Leveraging tools from large deviations theory, we prove that the best predictor-prescriptor pair is obtained by solving a distributionally robust optimization problem.
Extent	34 minutes
Subject	Mathematics; Operations research, mathematical programming; Probability theory and stochastic processes; Operation research
Type	Moving Image
File Format	video/mp4
Language	eng
Notes	Author affiliation: Ecole Polytechnique Federale de Laussane
Series	BIRS Workshop Lecture Videos (Banff, Alta)
Date Available	2018-09-06
Provider	Vancouver : University of British Columbia Library
Rights	Attribution-NonCommercial-NoDerivatives 4.0 International
DOI	10.14288/1.0371936
URI	http://hdl.handle.net/2429/67121
Affiliation	Non UBC
Peer Review Status	Unreviewed
Scholarly Level	Faculty
Rights URI	http://creativecommons.org/licenses/by-nc-nd/4.0/
Aggregated Source Repository	DSpace

Open Collections

BIRS Workshop Lecture Videos