Quantized Compressed Sensing by Rectified Linear Units
Quantized Compressed Sensing by Rectified Linear Units
Abstract This work is concerned with the problem of recovering high‐dimensional signals, which belong to a convex set of low‐complexity, from a small number of quantized measurements. We propose to estimate the signals via a convex program based on rectified linear units (ReLUs) for two different quantization schemes, namely one‐bit …