Performance Indicator in Multilinear Compressive Learning

TL;DR

This paper investigates how the initial reconstruction error in Multilinear Compressive Learning correlates with overall learning performance, providing a quick indicator for sensor configuration effectiveness without full system optimization.

Contribution

The study reveals that initial reconstruction error can serve as a reliable indicator of learning performance in MCL, simplifying sensor configuration assessment.

Findings

Reconstruction error correlates with learning performance.

Initial error can predict system effectiveness.

Sensor configuration impacts initial reconstruction error.

Abstract

Recently, the Multilinear Compressive Learning (MCL) framework was proposed to efficiently optimize the sensing and learning steps when working with multidimensional signals, i.e. tensors. In Compressive Learning in general, and in MCL in particular, the number of compressed measurements captured by a compressive sensing device characterizes the storage requirement or the bandwidth requirement for transmission. This number, however, does not completely characterize the learning performance of a MCL system. In this paper, we analyze the relationship between the input signal resolution, the number of compressed measurements and the learning performance of MCL. Our empirical analysis shows that the reconstruction error obtained at the initialization step of MCL strongly correlates with the learning performance, thus can act as a good indicator to efficiently characterize learning performances obtained from different sensor configurations without optimizing the entire system.