Robust Gradient Descent for Phase Retrieval

• URL: http://arxiv.org/abs/2410.10623v1
• Date: Mon, 14 Oct 2024 15:29:11 GMT
• Title: Robust Gradient Descent for Phase Retrieval
• Authors: Alex Buna, Patrick Rebeschini,
• Abstract summary: We investigate the ability to cope with fourth moment bounded noise in both the inputs (cos) and the inputs (cos) We propose a new step format that does not fit traditional adversarial scenarios.
• Score: 13.980824450716568
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in robust statistical learning has mainly tackled convex problems, like mean estimation or linear regression, with non-convex challenges receiving less attention. Phase retrieval exemplifies such a non-convex problem, requiring the recovery of a signal from only the magnitudes of its linear measurements, without phase (sign) information. While several non-convex methods, especially those involving the Wirtinger Flow algorithm, have been proposed for noiseless or mild noise settings, developing solutions for heavy-tailed noise and adversarial corruption remains an open challenge. In this paper, we investigate an approach that leverages robust gradient descent techniques to improve the Wirtinger Flow algorithm's ability to simultaneously cope with fourth moment bounded noise and adversarial contamination in both the inputs (covariates) and outputs (responses). We address two scenarios: known zero-mean noise and completely unknown noise. For the latter, we propose a preprocessing step that alters the problem into a new format that does not fit traditional phase retrieval approaches but can still be resolved with a tailored version of the algorithm for the zero-mean noise context.

Related papers

• Optimal sparse phase retrieval via a quasi-Bayesian approach [0.0]
  A signal need to be reconstructed using only the magnitude of its transformation while phase information remains inaccessible. We introduce a novel sparse quasi-Bayesian approach and provide the first theoretical guarantees for such an approach. Our results establish that the proposed Bayesian estimator achieves minimax-optimal convergence rates under sub-exponential noise.
  arXiv  Detail & Related papers  (2025-04-13T10:21:35Z)
• A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval [56.67706781191521]
  In this work, we present a robust phase retrieval problem where the task is to recover an unknown signal. Our proposed oracle avoids the need for computationally spectral descent, using a simple gradient step and outliers.
  arXiv  Detail & Related papers  (2024-09-07T06:37:23Z)
• Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing [84.97865583302244]
  We propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. DAPS significantly improves sample quality and stability across multiple image restoration tasks. For example, we achieve a PSNR of 30.72dB on the FFHQ 256 dataset for phase retrieval, which is an improvement of 9.12dB compared to existing methods.
  arXiv  Detail & Related papers  (2024-07-01T17:59:23Z)
• Label Noise: Correcting the Forward-Correction [0.0]
  Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. We propose an approach to tackling overfitting caused by label noise. Motivated by this observation, we propose imposing a lower bound on the training loss to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-07-24T19:41:19Z)
• Optimal Algorithms for the Inhomogeneous Spiked Wigner Model [89.1371983413931]
  We derive an approximate message-passing algorithm (AMP) for the inhomogeneous problem. We identify in particular the existence of a statistical-to-computational gap where known algorithms require a signal-to-noise ratio bigger than the information-theoretic threshold to perform better than random.
  arXiv  Detail & Related papers  (2023-02-13T19:57:17Z)
• A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem [7.624866197576227]
  We present a neural network warm-start approach for solving the inverse scattering problem. An initial guess for the optimization problem is obtained using a trained neural network. The algorithm remains robust to noise in the scattered field measurements and also converges to the true solution for limited aperture data.
  arXiv  Detail & Related papers  (2022-12-16T22:18:48Z)
• Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval [1.7767466724342065]
  We present a way leveraging the prior implicitly learned by a denoiser to solve phase retrieval problems by incorporating it in a classical framework. Compared to performant denoising-based algorithms for phase retrieval, we showcase competitive performance with notable measurements on in-distribution images and notable out-of-distribution images.
  arXiv  Detail & Related papers  (2022-11-02T05:08:50Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• Point Cloud Denoising via Momentum Ascent in Gradient Fields [72.93429911044903]
  gradient-based method was proposed to estimate the gradient fields from the noisy point clouds using neural networks. We develop a momentum gradient ascent method that leverages the information of previous iterations in determining the trajectories of the points. Experiments demonstrate that the proposed method outperforms state-of-the-art approaches with a variety of point clouds, noise types, and noise levels.
  arXiv  Detail & Related papers  (2022-02-21T10:21:40Z)
• Learning based signal detection for MIMO systems with unknown noise statistics [84.02122699723536]
  This paper aims to devise a generalized maximum likelihood (ML) estimator to robustly detect signals with unknown noise statistics. In practice, there is little or even no statistical knowledge on the system noise, which in many cases is non-Gaussian, impulsive and not analyzable. Our framework is driven by an unsupervised learning approach, where only the noise samples are required.
  arXiv  Detail & Related papers  (2021-01-21T04:48:15Z)
• Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser [7.7288480250888]
  We develop a robust and general methodology for making use of implicit priors in deep neural networks. A CNN trained to perform blind (i.e., with unknown noise level) least-squares denoising is presented. A generalization of this algorithm to constrained sampling provides a method for using the implicit prior to solve any linear inverse problem.
  arXiv  Detail & Related papers  (2020-07-27T15:40:46Z)
• When deep denoising meets iterative phase retrieval [5.639904484784126]
  Conventional algorithms for retrieving the phase suffer when noise is present but display global convergence when given clean data. Here, we combine iterative methods from phase retrieval with image statistics from deep denoisers, via regularization-by-denoising. The resulting methods inherit the advantages of each approach and outperform other noise-robust phase retrieval algorithms.
  arXiv  Detail & Related papers  (2020-03-03T21:00:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.