Multi-Stage Sparse Resource Allocation for Control of Spreading Processes over Networks

TL;DR

This paper introduces a convex optimization and dynamic programming-based method for sparsely allocating resources over time to control spreading processes like epidemics and wildfires on large networks, minimizing outbreak risk.

Contribution

It presents a novel approach combining convex optimization and dynamic programming for sparse, multi-stage resource allocation to control spreading processes on networks.

Findings

Effective in reducing outbreak risk with limited resources

Applicable to large network structures due to sparsity focus

Provides a systematic framework for dynamic resource management

Abstract

In this paper we propose a method for sparse dynamic allocation of resources to bound the risk of spreading processes, such as epidemics and wildfires, using convex optimization and dynamic programming techniques. Here, risk is defined as the risk of an outbreak, i.e. the product of the probability of an outbreak occurring over a time interval and the future impact of that outbreak, and we can allocate budgeted resources each time step to bound or minimize the risk. Our method in particular provides sparsity of resources, which is important due to the large network structures involved with spreading processes and has advantages when resources can not be distributed widely.