Metraipolis › archive › dc_a5bbebf19944

Distinguishability and Recovery for a Doubly Sparse Spiked Wigner Model — arXiv:2610.23033

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23033
License (as archived)
CC0-1.0
Archived
2026-10-19T09:21:22.364Z
SHA-256 of the archived text
1c088468af20f8c326a27d9d1b7222eb29a5728fc97767315477bdc410a2f69a
Stable URL of this page
https://metraipolis.com/documento/dc_a5bbebf19944

How to cite

Distinguishability and Recovery for a Doubly Sparse Spiked Wigner Model — arXiv:2610.23033 — arXiv (en), https://arxiv.org/abs/2610.23033 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5bbebf19944 (Metraipolis archive dc_a5bbebf19944, sha256 1c088468af20f8c326a27d9d1b7222eb29a5728fc97767315477bdc410a2f69a)
BibTeX
@misc{dca5bbebf19944,
  title = {Distinguishability and Recovery for a Doubly Sparse Spiked Wigner Model — arXiv:2610.23033},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23033},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5bbebf19944; sha256 1c088468af20f8c326a27d9d1b7222eb29a5728fc97767315477bdc410a2f69a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23033. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study distinguishability and recovery of a sparse rank-one signal in a spiked Wigner model with independently sparse noise through a variety of algorithms and parameter regimes. The signal and noise have separate sparsity parameters, while the signal-to-noise ratio (SNR) remains of constant order as the matrix size grows. For sub-Gaussian noise and spikes whose nonzero coordinates are bounded away from zero, a leave-one-out quadratic thresholding procedure (a generalization of Ding et al., 2024) identifies the support. Sign synchronization yields exact recovery for a Rademacher spike, and spectral refinement yields strong recovery. The quadratic thresholding search parameter gives an explicit tradeoff between signal sparsity, noise sparsity, and computational cost. We also study extensions to sub-Gaussian spike priors through diagonal and quadratic thresholding. For Rademacher spikes with continuous nonzero noise, we develop an identical search algorithm that exploits unblurred signal entries, the existence of which permits distinguishability; connectivity of the graph they reveal provides a sufficient condition for exact recovery. These guarantees do not require moment assumptions on the continuous noise distribution. Together with our previous PCA results (Dumitriu et al., 2026), our analysis covers almost the entire space of parameters and regimes for distinguishing and recovering in our doubly sparse spiked Wigner model.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.23033 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:17:41.707Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).