Risk-averse decisions improve reliability across multiple outage levels

Risk-Averse Decision Making with Multi-Level Reliability Guarantees

Information TheoryMachine Learning

Summary

Sometimes, engineers need to design systems that work reliably under different risk levels, like avoiding outages in wireless networks. The authors study how to make decisions that balance these different risk targets at the same time, even when the true system state is uncertain. They connect this problem to a method called 'conformal prediction' and create a new way to optimize decisions across different reliability goals. Their tests show the trade-offs and costs involved when using one policy to meet multiple risk levels.

What this means in practice

Authors

Amirmohammad Farzaneh, Osvaldo Simeone

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.