On One-Bit Quantization
Information Theory
2022-02-14 v1 Machine Learning
math.IT
Abstract
We consider the one-bit quantizer that minimizes the mean squared error for a source living in a real Hilbert space. The optimal quantizer is a projection followed by a thresholding operation, and we provide methods for identifying the optimal direction along which to project. As an application of our methods, we characterize the optimal one-bit quantizer for a continuous-time random process that exhibits low-dimensional structure. We numerically show that this optimal quantizer is found by a neural-network-based compressor trained via stochastic gradient descent.
Keywords
Cite
@article{arxiv.2202.05292,
title = {On One-Bit Quantization},
author = {Sourbh Bhadane and Aaron B. Wagner},
journal= {arXiv preprint arXiv:2202.05292},
year = {2022}
}