编码衍射图样相位恢复的稳定恢复与良性过参数化景观
Stable Recovery and Benign Overparameterized Landscapes for Phase Retrieval from Coded Diffraction Patterns
浏览论文内容
中文总结 AI 辅助
针对编码衍射图样相位恢复，证明使用对数数量随机掩模时，PhaseLift型凸程序达到高斯型稳定恢复界，且非凸分解损失在过参数化宽度下具有良性景观，所有临界点对应真实信号。
中文摘要 AI 辅助
编码衍射图样（CDP）为相位恢复提供了结构化的、物理相关的模型，但由公共掩模产生的傅里叶测量之间的依赖性使得尖锐的稳定性分析具有挑战性。对于固定的单位范数信号 $\boldsymbol{x}_\star \in \mathbb{C}^n$，令 $\boldsymbol{X}_\star=\boldsymbol{x}_\star\boldsymbol{x}_\star^*$，并令 $\mathcal A$ 为提升的CDP测量算子。我们证明，使用 $L=O(\log n)$ 个随机掩模，以下均匀下等距性质以高概率成立：$\\|\boldsymbol{X}-\boldsymbol{X}_\star\\|_F \lesssim \log^2(2n) \frac{\\|\mathcal A(\boldsymbol{X}-\boldsymbol{X}_\star)\\|_2}{\sqrt{nL}}, \boldsymbol{X}\succeq\boldsymbol{0},$ 由此我们得出两个推论。第一，对于 $\boldsymbol{y}=\mathcal A(\boldsymbol{X}_\star)+\boldsymbol{e}$，PhaseLift型凸程序达到高斯型稳定恢复界 $\\|\widehat{\boldsymbol{X}}-\boldsymbol{X}_\star\\|_F \lesssim \frac{\log^2(2n)}{\sqrt{nL}}\\|\boldsymbol{e}\\|_2.$ 第二，在无噪声情形下，当因子宽度满足 $r = O(\log^5(2n))$ 时，非凸分解损失具有良性景观：每个二阶临界点 $\boldsymbol{V}\in\mathbb C^{n\times r}$ 满足 $\boldsymbol{V}\boldsymbol{V}^*=\boldsymbol{X}_\star$。关键要素是对依赖的CDP测量矩阵的行子集的一致算子范数界，它允许移除一组自适应选择的受控行，同时保持切向注入性。
英文摘要
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.
发表机构
- The Hong Kong University of Science and Technology（香港科技大学）
- The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。
