Constant-Expansion Suffices for Compressed Sensing with Generative Priors

Authors: Constantinos Daskalakis, Dhruv Rohatgi, Emmanouil Zampetakis

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main contributions are mathematical in nature. We establish the notion of pseudo-Lipschitzness, along with a concentration inequality for random pseudo-Lipschitz functions, and random matrices, and we use our results to further the theoretical understanding of the non-convex optimization landscape arising in compressed sensing with deep generative priors.
Researcher Affiliation Academia Constantinos Daskalakis MIT costis@mit.edu Dhruv Rohatgi MIT drohatgi@mit.edu Manolis Zampetakis MIT mzampet@mit.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
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 No The paper is theoretical and does not describe experiments that would involve using a specific publicly available dataset for training.
Dataset Splits No The paper is theoretical and does not provide specific dataset split information for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not provide specific software dependencies with version numbers needed to replicate experiments.
Experiment Setup No The paper is theoretical and does not provide specific experimental setup details such as hyperparameter values or training configurations.