Risk-Averse Decision Making with Multi-Level Reliability Guarantees

2026-09-10

AI Summary

本文研究了在系统状态不确定下，通过优化嵌套预测集来最大化不同目标中断水平性能证书的加权平均值的问题。

Abstract

Many applications in engineering, including wireless broadcasting, require designs that provide performance certificates at different target outage levels. This paper studies the problem of maximizing the weighted average of such certificates in the presence of uncertainty about the true system state. The problem is shown to be equivalent to an optimization over nested prediction sets, connecting to the literature on conformal prediction and extending prior art on single-level risk-averse decision making. Furthermore, we derive a dual formulation that decouples optimization across input values. Numerical experiments on a diversity-based wireless transmission system illustrate the cost of enforcing multi-level certificates with a single shared policy and trace the Pareto trade-off between multiple reliability levels.

Problem

• risk-averse decision making
• reliability guarantees
• uncertainty

Innovation

• nested prediction sets
• multi-level reliability guarantees
• dual formulation