Convex Phase Retrieval without Lifting via PhaseMax
Authors: Tom Goldstein, Christoph Studer
ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We compare our approach to other phase retrieval methods and demonstrate that our theory accurately predicts the success of Phase Max. In Figure 2, we use random Gaussian test problems and the accelerated gradient-based solver described in (Goldstein et al., 2014) to plot the empirical and theoretical probabilities of exact signal recovery for n = 100 and n = 500 measurements while varying the accuracy β = angle(ˆx, x0) of the initial guess. |
| Researcher Affiliation | Academia | 1University of Maryland 2Cornell University. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statements or links regarding the availability of open-source code for the methodology described. |
| Open Datasets | No | The paper refers to using "random Gaussian measurements" and "random Gaussian test problems" but does not specify any named, publicly available datasets with concrete access information (e.g., a link, DOI, or formal citation). |
| Dataset Splits | No | The paper discusses performing experiments using "random Gaussian test problems" but does not explicitly specify training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using an "accelerated gradient-based solver described in (Goldstein et al., 2014)" but does not provide specific version numbers for any software libraries or dependencies. |
| Experiment Setup | No | The paper states the criterion for exact recovery as "relative error of the recovered signal fell below 10 5", but it does not provide specific experimental setup details such as hyperparameters (e.g., learning rate, batch size, epochs) or training configurations. |