A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery
Authors: Ali Mousavi, Gautam Dasarathy, Richard G. Baraniuk
ICLR 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the significant improvement our method obtains over competing methods through a series of experiments. ... We now illustrate the performance of Deep SSRR against competing methods in several problems. ... We use the grayscale version of CIFAR-10 dataset (50,000 training + 10,000 test 32 32 images). ... Figure 3(a) shows the size of embedding M as a function of the isometry constant ϵ for different methods. |
| Researcher Affiliation | Collaboration | Ali Mousavi Google AI alimous@google.com Gautam Dasarathy Arizona State University gautamd@asu.edu Richard G. Baraniuk Rice University richb@rice.edu |
| Pseudocode | Yes | Algorithm 1 Learning a Near-Isometric Embedding |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that its source code is open or publicly available. |
| Open Datasets | Yes | We use the grayscale version of CIFAR-10 dataset (50,000 training + 10,000 test 32 32 images). ... For training, we have used batches of 128 images of size 64 64 from Image Net (Russakovsky et al., 2015). |
| Dataset Splits | Yes | Our training and validation sets include 10,000 and 500 images, respectively. |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions software like 'ADAM optimizer' and 'BM3D denoiser' and the 'LASSO', but it does not specify any version numbers for these or other software dependencies. |
| Experiment Setup | Yes | Deep SSRR is trained with an initial learning rate of 0.001 that is changed to 0.0001 when the validation error stops decreasing. For training, we have used batches of 128 images of size 64 64 from Image Net. |