Data-Driven Optimization: A Reproducing Kernel Hilbert Space Approach

Dimitris Bertsimas () and Nihal Koduri ()
Additional contact information
Dimitris Bertsimas: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
Nihal Koduri: Operations Research Center, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139

Operations Research, 2022, vol. 70, issue 1, 454-471

Abstract: We present two methods, based on regression in reproducing kernel Hilbert spaces, for solving an optimization problem with uncertain parameters for which we have historical data, including auxiliary data. The first method approximates the objective function and the second approximates the optimizer. We provide finite sample guarantees and prove asymptotic optimality for both methods. Computational experiments suggest that at least the second method overcomes a curse of dimensionality that afflicts existing methods, extrapolates better to unseen data, and achieves a many-fold decrease in sample complexity even for small dimensions.

Keywords: Optimization; data-driven optimization; prescriptive analytics; reproducing kernel Hilbert space; regression; optimality (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://dx.doi.org/10.1287/opre.2020.2069 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:oropre:v:70:y:2022:i:1:p:454-471

Access Statistics for this article

More articles in Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().