🤖 AI Summary
This work proposes the first polynomial-time algorithm for phase retrieval under heavy-tailed noise and simultaneous adversarial corruption of both sensing vectors and measurements. By integrating robust spectral initialization with state-of-the-art robust principal component analysis, the method leverages tools from high-dimensional statistical estimation and adversarially robust learning theory to accurately recover an $n$-dimensional signal up to a global phase, using only near-linear sample complexity ($O(n \log n)$). This approach overcomes the limitations of prior methods that relied on computationally intractable, exponential-time procedures, thereby achieving the first efficient and provably robust solution for phase retrieval in the challenging setting of heavy-tailed noise combined with dual adversarial contamination.
📝 Abstract
Phase retrieval is the classical problem of recovering a signal $x^* \in \mathbb{R}^n$ from its noisy phaseless measurements $y_i = \langle a_i, x^* \rangle^2 + \zeta_i$ (where $\zeta_i$ denotes noise, and $a_i$ is the sensing vector) for $i \in [m]$. The problem of phase retrieval has a rich history, with a variety of applications such as optics, crystallography, heteroscedastic regression, astrophysics, etc. A major consideration in algorithms for phase retrieval is robustness against measurement errors. In recent breakthroughs in algorithmic robust statistics, efficient algorithms have been developed for several parameter estimation tasks such as mean estimation, covariance estimation, robust principal component analysis (PCA), etc. in the presence of heavy-tailed noise and adversarial corruptions. In this paper, we study efficient algorithms for robust phase retrieval with heavy-tailed noise when a constant fraction of both the measurements $y_i$ and the sensing vectors $a_i$ may be arbitrarily adversarially corrupted. For this problem, Buna and Rebeschini (AISTATS 2025) very recently gave an exponential time algorithm with sample complexity $O(n \log n)$. Their algorithm needs a robust spectral initialization, specifically, a robust estimate of the top eigenvector of a covariance matrix, which they deemed to be beyond known efficient algorithmic techniques (similar spectral initializations are a key ingredient of a large family of phase retrieval algorithms). In this work, we make a connection between robust spectral initialization and recent algorithmic advances in robust PCA, yielding the first polynomial-time algorithms for robust phase retrieval with both heavy-tailed noise and adversarial corruptions, in fact with near-linear (in $n$) sample complexity.