Information Flow Optimization in Inference Networks

TL;DR

This paper formulates the problem of maximizing information flow in sensor networks for inference tasks as a Network Utility Maximization problem, enabling improved inference performance over traditional max-flow approaches.

Contribution

It introduces a novel utility-based optimization framework for rate-constrained inference in sensor networks, applicable to parameter estimation and hypothesis testing.

Findings

Proposed formulation outperforms max-flow in inference accuracy.

Applicable to multi-terminal estimation and binary hypothesis testing.

Validated through simulations showing improved performance.

Abstract

The problem of maximizing the information flow through a sensor network tasked with an inference objective at the fusion center is considered. The sensor nodes take observations, compress and send them to the fusion center through a network of relays. The network imposes capacity constraints on the rate of transmission in each connection and flow conservation constraints. It is shown that this rate-constrained inference problem can be cast as a Network Utility Maximization problem by suitably defining the utility functions for each sensor, and can be solved using existing techniques. Two practical settings are analyzed: multi-terminal parameter estimation and binary hypothesis testing. It is verified via simulations that using the proposed formulation gives better inference performance than the Max-Flow solution that simply maximizes the total bit-rate to the fusion center.