Dynamic optimization with side information

07/17/2019
by   Dimitris Bertsimas, et al.
0

We present a data-driven framework for incorporating side information in dynamic optimization under uncertainty. Specifically, our approach uses predictive machine learning methods (such as k-nearest neighbors, kernel regression, and random forests) to weight the relative importance of various data-driven uncertainty sets in a robust optimization formulation. Through a novel measure concentration result for local machine learning methods, we prove that the proposed framework is asymptotically optimal for stochastic dynamic optimization with covariates. We also describe a general-purpose approximation for the proposed framework, based on overlapping linear decision rules, which is computationally tractable and produces high-quality solutions for dynamic problems with many stages. Across a variety of examples in shipment planning, inventory management, and finance, our method achieves improvements of up to 15 problems with twelve stages.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/11/2023

Multistage Stochastic Optimization via Kernels

We develop a non-parametric, data-driven, tractable approach for solving...
research
07/11/2018

Optimization over Continuous and Multi-dimensional Decisions with Observational Data

We consider the optimization of an uncertain objective over continuous a...
research
04/26/2019

From Predictions to Prescriptions in Multistage Optimization Problems

In this paper, we introduce a framework for solving finite-horizon multi...
research
11/27/2017

Bootstrap Robust Prescriptive Analytics

We address the problem of prescribing an optimal decision in a framework...
research
01/24/2023

Explainable Data-Driven Optimization: From Context to Decision and Back Again

Data-driven optimization uses contextual information and machine learnin...
research
03/04/2020

Safeguarded Learned Convex Optimization

Many applications require repeatedly solving a certain type of optimizat...
research
02/22/2014

From Predictive to Prescriptive Analytics

In this paper, we combine ideas from machine learning (ML) and operation...

Please sign up or login with your details

Forgot password? Click here to reset