One-Bit Phase Retrieval: Optimal Rates and Efficient Algorithms

📅 2024-05-08
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

204K/year
🤖 AI Summary
This paper studies the 1-bit phase retrieval problem: reconstructing a real signal $mathbf{x} in mathbb{R}^n$—either dense or $k$-sparse—from $m$ 1-bit measurements $mathrm{sign}(|mathbf{a}_i^ op mathbf{x}| - au)$, where $mathbf{a}_i sim mathcal{N}(0,I_n)$. We establish the first information-theoretically optimal estimation error bounds, demonstrating that phase information is unnecessary in 1-bit compressed sensing. We propose a one-sided $ell_1$ gradient descent algorithm with spectral initialization, achieving linear convergence and near-optimal statistical accuracy. Key technical innovations include random hyperplane tessellation analysis, local restricted approximate invertibility characterization, and thresholded gradient updates. Our theory yields optimal error rates $O((n/m)log(m/n))$ for dense signals and $O((k/m)log(mn/k^2))$ for $k$-sparse signals. The algorithm attains sample complexities of $O(n)$ and $O(k^2 log n cdot log^2 (m/k))$, respectively—achieving both computational efficiency and statistical optimality.

Technology Category

Application Category

📝 Abstract
In this paper, we study the sample complexity and develop efficient optimal algorithms for 1-bit phase retrieval: recovering a signal $mathbf{x}inmathbb{R}^n$ from $m$ phaseless bits ${mathrm{sign}(|mathbf{a}_i^ opmathbf{x}|- au)}_{i=1}^m$ generated by standard Gaussian $mathbf{a}_i$s. By investigating a phaseless version of random hyperplane tessellation, we show that (constrained) hamming distance minimization uniformly recovers all unstructured signals with Euclidean norm bounded away from zero and infinity to the error $mathcal{O}((n/m)log(m/n))$, and $mathcal{O}((k/m)log(mn/k^2))$ when restricting to $k$-sparse signals. Both error rates are shown to be information-theoretically optimal, up to a logarithmic factor. Intriguingly, the optimal rate for sparse recovery matches that of 1-bit compressed sensing, suggesting that the phase information is non-essential for 1-bit compressed sensing. We also develop efficient algorithms for 1-bit (sparse) phase retrieval that can achieve these error rates. Specifically, we prove that (thresholded) gradient descent with respect to the one-sided $ell_1$-loss, when initialized via spectral methods, converges linearly and attains the near optimal reconstruction error, with sample complexity $mathcal{O}(n)$ for unstructured signals and $mathcal{O}(k^2log(n)log^2(m/k))$ for $k$-sparse signals. Our proof is based upon the observation that a certain local (restricted) approximate invertibility condition is respected by Gaussian measurements.
Problem

Research questions and friction points this paper is trying to address.

Develops optimal algorithms for 1-bit phase retrieval from phaseless Gaussian measurements.
Establishes information-theoretically optimal error rates for unstructured and sparse signal recovery.
Proves efficient gradient descent methods achieve near-optimal reconstruction with linear convergence.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Hamming distance minimization for uniform signal recovery
Gradient descent with spectral initialization for efficient algorithms
Achieving optimal error rates with local invertibility condition
🔎 Similar Papers
No similar papers found.