Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

Aleksandr Pak, Justin Ko, Florent Krzakala

Abstract

In this paper, we study a spiked Wigner problem with an inhomogeneous noise profile. Our aim in this problem is to recover the signal passed through an inhomogeneous low-rank matrix channel. While the information-theoretic performances are well-known, we focus on the algorithmic problem. We derive an approximate message-passing algorithm (AMP) for the inhomogeneous problem and show that its rigorous state evolution coincides with the information-theoretic optimal Bayes fixed-point equations. We identify in particular the existence of a statistical-to-computational gap where known algorithms require a signal-to-noise ratio bigger than the information-theoretic threshold to perform better than random. Finally, from the adapted AMP iteration we deduce a simple and efficient spectral method that can be used to recover the transition for matrices with general variance profiles. This spectral method matches the conjectured optimal computational phase transition.
BibTeX
@inproceedings{pak2023optimal,
  author = {Aleksandr Pak and Justin Ko and Florent Krzakala},
  title = {{Optimal Algorithms for the Inhomogeneous Spiked Wigner Model}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2023},
  url = {https://openreview.net/forum?id=xNUmTRYtV1},
}
Figure