Sparse constrained projection approximation subspace tracking

TL;DR

This paper revisits the CPAST algorithm, providing non-asymptotic error bounds, and introduces a sparse variant that leverages covariance sparsity, with theoretical analysis and empirical validation.

Contribution

The paper derives the first non-asymptotic error bounds for CPAST and proposes a new sparse version that exploits covariance sparsity.

Findings

Non-asymptotic error bounds for CPAST

Effective sparse modification exploits covariance structure

Empirical validation on simulated and real data

Abstract

In this paper we revisit the well-known constrained projection approximation subspace tracking algorithm (CPAST) and derive, for the first time, non-asymptotic error bounds. Furthermore, we introduce a novel sparse modification of CPAST which is able to exploit sparsity in the underlying covariance structure. We present a non-asymptotic analysis of the proposed algorithm and study its empirical performance on simulated and real data.