BLISS: Global Blind Identification of Linear Systems with Sparse Inputs

TL;DR

This paper introduces BLISS, a method that leverages sparse inputs to achieve global blind identification of linear systems, connecting it to dictionary learning and providing theoretical guarantees.

Contribution

It establishes a novel connection between blind linear system identification and sparse dictionary learning, enabling new global identifiability results.

Findings

Global identifiability guarantees for blind system identification.

Empirical demonstration of recovering systems from a single trajectory.

Application of ADMM for successful system recovery with sufficient data.

Abstract

Linear system identification and sparse dictionary learning can both be seen as structured matrix factorization problems. However, these two problems have historically been studied in isolation by the systems theory and machine learning communities. Although linear system identification enjoys a mature theory when inputs are known, blind linear system identification remains poorly understood beyond restrictive settings. In contrast, complete sparse dictionary learning has recently benefited from strong global identifiability results and scalable nonconvex algorithms. In this work, we bridge these two areas by showing that under a sparse input assumption, fully observed blind system identification becomes a generalization of complete dictionary learning. This connection allows us to develop global identifiability guarantees for blind system identification, by leveraging techniques from the complete dictionary learning literature. We further show empirically that a principled application of the alternating direction method of multipliers can globally recover the ground-truth system from a single trajectory, provided sufficient samples and input sparsity.