Global Guarantees for Blind Demodulation with Generative Priors

Authors: Paul Hand, Babhru Joshi

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We now empirically show that Algorithm 1 can remove distortions present in the dataset. We consider the image recovery task of removing distortions that were synthetically introduced to the MNIST dataset.
Researcher Affiliation Academia Paul Hand Dept. of Mathematics and College of Computer Science and Information Northeastern University, MA p.hand@northeastern.edu Babhru Joshi Dept. of Mathematics University of British Columbia, BC b.joshi@math.ubc.ca
Pseudocode Yes Algorithm 1 Alternating descent algorithm for (2)
Open Source Code No The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes We consider the image recovery task of removing distortions that were synthetically introduced to the MNIST dataset. Prior to training the generators, the images in the MNIST dataset and the distortion dataset were resized to 64x64 images.
Dataset Splits No The paper mentions training generators on the MNIST dataset but does not provide explicit details about training, validation, or test dataset splits (e.g., percentages, sample counts, or predefined splits).
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions using DCGAN but does not provide specific version numbers for this or any other software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup Yes We used DCGAN with a learning rate of 0.0002 and latent code dimension of 50... We used the Stochastic Gradient Descent algorithm with the step size set to 1 and momentum set to 0.9. ... after 500 iterations.