367 citations · 1.4k across the 72 of their papers we have counts for
5 papers · 1 filter
Characterization of the equivalence of robustification and regularization in linear and matrix regression
Dimitris Bertsimas, Martin S. Copenhaver
The notion of developing statistical methods in machine learning which are robust to adversarial perturbations in the underlying data has been the subject of increasing interest in…
Robust Sample Average Approximation
Dimitris Bertsimas, Vishal Gupta, Nathan Kallus
Sample average approximation (SAA) is a widely popular approach to data-driven decision-making under uncertainty. Under mild assumptions, SAA is both tractable and enjoys strong as…
A Comparison of Monte Carlo Tree Search and Mathematical Optimization for Large Scale Dynamic Resource Allocation
Dimitris Bertsimas, J. Daniel Griffith, Vishal Gupta +3
Dynamic resource allocation (DRA) problems are an important class of dynamic stochastic optimization problems that arise in a variety of important real-world applications. DRA prob…
From Predictive to Prescriptive Analytics
Dimitris Bertsimas, Nathan Kallus
In this paper, we combine ideas from machine learning (ML) and operations research and management science (OR/MS) in developing a framework, along with specific methods, for using…
Data-Driven Robust Optimization
Dimitris Bertsimas, Vishal Gupta, Nathan Kallus
The last decade witnessed an explosion in the availability of data for operations research applications. Motivated by this growing availability, we propose a novel schema for utili…