On Combining Machine Learning with Decision Making

TL;DR

This paper introduces a novel framework combining machine learning with decision making, applying it to a power grid repair problem, and provides new theoretical bounds on its generalization performance.

Contribution

It develops the MLOC framework for decision-aware learning and applies it to the ML&TRP, offering new covering number bounds for better understanding of generalization.

Findings

New covering number bounds for MLOC framework

Application of MLOC to power grid repair problem

Insights into how uncertainty affects decision-making

Abstract

We present a new application and covering number bound for the framework of "Machine Learning with Operational Costs (MLOC)," which is an exploratory form of decision theory. The MLOC framework incorporates knowledge about how a predictive model will be used for a subsequent task, thus combining machine learning with the decision that is made afterwards. In this work, we use the MLOC framework to study a problem that has implications for power grid reliability and maintenance, called the Machine Learning and Traveling Repairman Problem ML&TRP. The goal of the ML&TRP is to determine a route for a "repair crew," which repairs nodes on a graph. The repair crew aims to minimize the cost of failures at the nodes, but as in many real situations, the failure probabilities are not known and must be estimated. The MLOC framework allows us to understand how this uncertainty influences the repair route. We also present new covering number generalization bounds for the MLOC framework.