Modeling Sparse Deviations for Compressed Sensing using Generative Models

Authors: Manik Dhar, Aditya Grover, Stefano Ermon

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we observe consistent improvements in reconstruction accuracy over competing approaches, especially in the more practical setting of transfer compressed sensing where a generative model for a data-rich, source domain aids sensing on a data-scarce, target domain. and 5. Experimental Evaluation
Researcher Affiliation Academia 1Computer Science Department, Stanford University, CA, USA.
Pseudocode No No pseudocode or clearly labeled algorithm blocks were found in the paper.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We considered the MNIST dataset of handwritten digits (Le Cun et al., 2010) and the OMNIGLOT dataset of handwritten characters (Lake et al., 2015).
Dataset Splits Yes For VAE training, we used the standard train/held-out splits of both datasets.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions general software or libraries (e.g., 'Tensorflow' is cited in references) but does not provide specific version numbers for software dependencies needed to replicate the experiment.
Experiment Setup Yes The architecture and other hyperparameter details are given in the Appendix.