Online Low-Rank Tensor Subspace Tracking from Incomplete Data by CP Decomposition using Recursive Least Squares

TL;DR

This paper introduces OLSTEC, an online tensor subspace tracking algorithm using CP decomposition and recursive least squares, which converges faster than existing online methods.

Contribution

The paper presents OLSTEC, a novel online tensor tracking algorithm that improves convergence speed over prior online algorithms using RLS and CP decomposition.

Findings

OLSTEC achieves faster convergence per iteration.

OLSTEC outperforms state-of-the-art online algorithms.

The method effectively tracks low-rank tensor subspaces in real-time.

Abstract

We propose an online tensor subspace tracking algorithm based on the CP decomposition exploiting the recursive least squares (RLS), dubbed OnLine Low-rank Subspace tracking by TEnsor CP Decomposition (OLSTEC). Numerical evaluations show that the proposed OLSTEC algorithm gives faster convergence per iteration comparing with the state-of-the-art online algorithms.