Metraipolis › archive › dc_bc03f9d197b3

Stable Recovery and Benign Overparameterized Landscapes for Phase Retrieval from Coded Diffraction Patterns — arXiv:2609.30825

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30825
License (as archived)
CC0-1.0
Archived
2026-10-08T03:11:28.578Z
SHA-256 of the archived text
38359240bcc84bd1139bb79d034641abc823787b10df7c7edd54ca9008208505
Stable URL of this page
https://metraipolis.com/documento/dc_bc03f9d197b3

How to cite

Stable Recovery and Benign Overparameterized Landscapes for Phase Retrieval from Coded Diffraction Patterns — arXiv:2609.30825 — arXiv (en), https://arxiv.org/abs/2609.30825 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc03f9d197b3 (Metraipolis archive dc_bc03f9d197b3, sha256 38359240bcc84bd1139bb79d034641abc823787b10df7c7edd54ca9008208505)
BibTeX
@misc{dcbc03f9d197b3,
  title = {Stable Recovery and Benign Overparameterized Landscapes for Phase Retrieval from Coded Diffraction Patterns — arXiv:2609.30825},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30825},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc03f9d197b3; sha256 38359240bcc84bd1139bb79d034641abc823787b10df7c7edd54ca9008208505},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30825. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coded diffraction patterns (CDPs) provide a structured and physically relevant model for phase retrieval, but the dependence among Fourier measurements generated by a common mask makes sharp stability analysis challenging. For a fixed unit-norm signal $\boldsymbol{x}_\star \in \mathbb{C}^n$, let $\boldsymbol{X}_\star=\boldsymbol{x}_\star\boldsymbol{x}_\star^*$, and let $\mathcal A$ be the lifted CDP measurement operator. We prove that, with $L=O(\log n)$ random masks, the following uniform lower isometry holds with high probability: $\|\boldsymbol{X}-\boldsymbol{X}_\star\|_F \lesssim \log^2(2n) \frac{\|\mathcal A(\boldsymbol{X}-\boldsymbol{X}_\star)\|_2}{\sqrt{nL}}, \boldsymbol{X}\succeq\boldsymbol{0},$ from which we derive two consequences. First, for $\boldsymbol{y}=\mathcal A(\boldsymbol{X}_\star)+\boldsymbol{e}$, PhaseLift-type convex programs achieve the Gaussian-type stable recovery bound $\|\widehat{\boldsymbol{X}}-\boldsymbol{X}_\star\|_F \lesssim \frac{\log^2(2n)}{\sqrt{nL}}\|\boldsymbol{e}\|_2.$ Second, in the noiseless case, the nonconvex factorized loss has a benign landscape when the factor width satisfies $r = O(\log^5(2n))$: every second-order critical point $\boldsymbol{V}\in\mathbb C^{n\times r}$ satisfies $\boldsymbol{V}\boldsymbol{V}^*=\boldsymbol{X}_\star$. The key ingredient is a uniform operator-norm bound over row subsets of the dependent CDP measurement matrix, which permits the removal of a controlled set of adaptively selected rows while preserving tangent injectivity.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-28 in math.IT).
Categorie arXiv: Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2609.30825 — 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 2026-10-08T02:45:36.787Z dalla pagina https://arxiv.org/catchup/math.IT/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).