Performance Indicator in Multilinear Compressive Learning
This work addresses a specific bottleneck in MCL for researchers, but it is incremental as it builds on an existing framework to improve performance analysis.
The paper tackles the problem of characterizing learning performance in Multilinear Compressive Learning (MCL) systems, showing that reconstruction error at initialization strongly correlates with learning performance, enabling efficient evaluation of sensor configurations without full system optimization.
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.