Closing the Gaps: Optimality of Sample Average Approximation for Data-Driven Newsvendor Problems

TL;DR

This paper establishes the optimal regret bounds for Sample Average Approximation in data-driven newsvendor problems with convex costs, clarifying how local and global convexity properties influence long-term decision-making performance.

Contribution

It proves the optimal regret bounds under both local and global strong convexity conditions, filling gaps in the theoretical understanding of SAA's performance in newsvendor problems.

Findings

SAA achieves a regret bound of (\,\,) under local strong convexity.

Any data-driven method has a lower bound of (\,) regret under global strong convexity.

Introduces a new gradient approximation technique and hard problem instances for analyzing regret.

Abstract

We study the regret performance of Sample Average Approximation (SAA) for data-driven newsvendor problems with general convex inventory costs. In literature, the optimality of SAA has not been fully established under both \alpha-global strong convexity and (\alpha,\beta)-local strong convexity (\alpha-strongly convex within the \beta-neighborhood of the optimal quantity) conditions. This paper closes the gaps between regret upper and lower bounds for both conditions. Under the (\alpha,\beta)-local strong convexity condition, we prove the optimal regret bound of \Theta(\log T/\alpha + 1/ (\alpha\beta)) for SAA. This upper bound result demonstrates that the regret performance of SAA is only influenced by \alpha and not by \beta in the long run, enhancing our understanding about how local properties affect the long-term regret performance of decision-making strategies. Under the \alpha-global strong convexity condition, we demonstrate that the worst-case regret of any data-driven method is lower bounded by \Omega(\log T/\alpha), which is the first lower bound result that matches the existing upper bound with respect to both parameter \alpha and time horizon T. Along the way, we propose to analyze the SAA regret via a new gradient approximation technique, as well as a new class of smooth inverted-hat-shaped hard problem instances that might be of independent interest for the lower bounds of broader data-driven problems.