Blind Deconvolutional Phase Retrieval via Convex Programming

Authors: Ali Ahmed, Alireza Aghasi, Paul Hand

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Additionally, we provide an ADMM implementation of the method and provide numerical experiments that verify the theory. Numerical experiments show that, using this algorithm, one can successfully recover a blurred image from the magnitude only measurements of its Fourier spectrum.
Researcher Affiliation Academia Ali Ahmed Department of Electrical Engineering Information Technology University Lahore, Pakistan. ali.ahmed@itu.edu.pk Alireza Aghasi Department of Business Analytics Georgia State University Atlanta, GA. aaghasi@gsu.edu Paul Hand College of Computer and Information Science Northeastern University Boston, MA. p.hand@northeastern.edu
Pseudocode No The paper refers to an ADMM implementation and moving technical details to supplementary material, but does not include a structured pseudocode or algorithm block within the provided text.
Open Source Code No The paper does not contain any explicit statement about releasing source code or provide any links to a code repository.
Open Datasets No The paper describes generating data based on "standard Gaussian matrices" and testing different combinations of parameters (n and k), but it does not mention or provide access to a named, publicly available dataset used for training in the conventional sense.
Dataset Splits No The paper describes running experiments for "100 different combinations of n and k" and checking for convergence, but it does not specify standard dataset splits (e.g., 80/10/10 split, k-fold cross-validation) for training, validation, or testing.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper mentions an "ADMM implementation" but does not list any specific software dependencies or library versions needed to replicate the experiments.
Experiment Setup Yes To obtain the diagram on the left panel, for each fixed value of m, we run the algorithm for 100 different combinations of n and k, each time using a different set of Gaussian matrices B and C. If the algorithm converges to a sufficiently close neighborhood of the ground-truth solution (a distance less than 1% of the solution s ℓ2 norm), we label the experiment as successful.