Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
ICML, pp. 6216-6225, 2020.
We have established sample complexity bounds for both noiseless and noisy 1-bit compressive sensing with generative models
The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of the vector. Motivated by recent advances in compressive sensing with generative models, where a generative modeling assumption replaces the usual sparsity assu...More
PPT (Upload PPT)