Asymptotically Optimal Distributionally Robust Solutions through Forecasting and Operations Decentralization

TL;DR

This paper introduces a decentralized framework for two-stage risk-averse distributionally robust optimization that simplifies decision-making, achieves asymptotic optimality, and outperforms existing methods in computational efficiency and practical applications.

Contribution

The paper proposes a novel decentralized approach with a two-point communication scheme that guarantees asymptotic optimality for complex DRO problems.

Findings

Decentralized approach converges to optimal solutions as problem size increases.

Two-point distribution communication simplifies the forecasting process.

Method outperforms traditional approximation methods in real-world data tests.

Abstract

Two-stage risk-averse distributionally robust optimization (DRO) problems are ubiquitous across many engineering and business applications. Despite their promising resilience, two-stage DRO problems are generally computationally intractable. To address this challenge, we propose a simple framework by decentralizing the decision-making process into two specialized teams: forecasting and operations. This decentralization aligns with prevalent organizational practices, in which the operations team uses the information communicated from the forecasting team as input to make decisions. We formalize this decentralized procedure as a bilevel problem to design a communicated distribution that can yield asymptotic optimal solutions to original two-stage risk-averse DRO problems. We identify an optimal solution that is surprisingly simple: The forecasting team only needs to communicate a two-point distribution to the operations team. Consequently, the operations team can solve a highly tractable and scalable optimization problem to identify asymptotic optimal solutions. Specifically, as the magnitude of the problem parameters (including the uncertain parameters and the first-stage capacity) increases to infinity at an appropriate rate, the cost ratio between our induced solution and the original optimal solution converges to one, indicating that our decentralized approach yields high-quality solutions. We compare our decentralized approach against the truncated linear decision rule approximation and demonstrate that our approach has broader applicability and superior computational efficiency while maintaining competitive performance. Using real-world sales data, we have demonstrated the practical effectiveness of our strategy. The finely tuned solution significantly outperforms traditional sample-average approximation methods in out-of-sample performance.