Robustness Analysis of Preconditioned Successive Projection Algorithm for General Form of Separable NMF Problem
This addresses a theoretical gap for practitioners in fields like topic modeling and hyperspectral imaging, though it is incremental as it extends prior work.
The paper tackles the robustness of the preconditioned successive projection algorithm for separable nonnegative matrix factorization under realistic conditions where the dimension exceeds the factorization rank, proving that it remains robust to noise.
The successive projection algorithm (SPA) has been known to work well for separable nonnegative matrix factorization (NMF) problems arising in applications, such as topic extraction from documents and endmember detection in hyperspectral images. One of the reasons is in that the algorithm is robust to noise. Gillis and Vavasis showed in [SIAM J. Optim., 25(1), pp. 677-698, 2015] that a preconditioner can further enhance its noise robustness. The proof rested on the condition that the dimension $d$ and factorization rank $r$ in the separable NMF problem coincide with each other. However, it may be unrealistic to expect that the condition holds in separable NMF problems appearing in actual applications; in such problems, $d$ is usually greater than $r$. This paper shows, without the condition $d=r$, that the preconditioned SPA is robust to noise.