Compressed Sensing using Generative Models

Authors: Ashish Bora, Ajil Jalal, Eric Price, Alexandros G. Dimakis

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We compare the performance of our algorithm with baselines. We show a plot of per pixel reconstruction error as we vary the number of measurements. The vertical bars indicate 95% confidence intervals.
Researcher Affiliation Academia 1University of Texas at Austin, Department of Computer Science 2University of Texas at Austin, Department of Electrical and Computer Engineering.
Pseudocode No The paper describes the algorithm in Section 2 'Our Algorithm' using prose, but it does not provide a formal pseudocode block or algorithm listing.
Open Source Code Yes Code for experiments in the paper can be found at: https://github.com/Ashish Bora/csgm
Open Datasets Yes The MNIST dataset consists of about 60, 000 images of handwritten digits, where each image is of size 28 28 (Le Cun et al., 1998). ... Celeb A is a dataset of more than 200, 000 face images of celebrities (Liu et al., 2015).
Dataset Splits No The paper mentions using a 'held out test set' but does not specify explicit training/validation/test splits (e.g., percentages or sample counts) or cross-validation setup.
Hardware Specification No The paper does not specify any particular hardware (e.g., CPU, GPU models, or memory) used for running the experiments.
Software Dependencies No The paper mentions using the Adam optimizer and implies a TensorFlow implementation through a reference (Kim, 2017), but it does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes We train the VAE using the Adam optimizer (Kingma & Ba, 2014) with a mini-batch size 100 and a learning rate of 0.001. We use λ = 0.1 in Eqn. (3). ... Each update used the Adam optimizer (Kingma & Ba, 2014) with minibatch size 64, learning rate 0.0002 and β1 = 0.5. We use λ = 0.001 in Eqn. (3).