English

Do algorithms and barriers for sparse principal component analysis extend to other structured settings?

Machine Learning 2024-01-02 v2 Machine Learning

Abstract

We study a principal component analysis problem under the spiked Wishart model in which the structure in the signal is captured by a class of union-of-subspace models. This general class includes vanilla sparse PCA as well as its variants with graph sparsity. With the goal of studying these problems under a unified statistical and computational lens, we establish fundamental limits that depend on the geometry of the problem instance, and show that a natural projected power method exhibits local convergence to the statistically near-optimal neighborhood of the solution. We complement these results with end-to-end analyses of two important special cases given by path and tree sparsity in a general basis, showing initialization methods and matching evidence of computational hardness. Overall, our results indicate that several of the phenomena observed for vanilla sparse PCA extend in a natural fashion to its structured counterparts.

Keywords

Cite

@article{arxiv.2307.13535,
  title  = {Do algorithms and barriers for sparse principal component analysis extend to other structured settings?},
  author = {Guanyi Wang and Mengqi Lou and Ashwin Pananjady},
  journal= {arXiv preprint arXiv:2307.13535},
  year   = {2024}
}
R2 v1 2026-06-28T11:39:43.567Z