NBIHT: An Efficient Algorithm for 1-bit Compressed Sensing with Optimal Error Decay Rate

TL;DR

This paper introduces NBIHT, a theoretically analyzed and computationally efficient algorithm for one-bit compressed sensing that achieves near-optimal error decay rates matching information-theoretic bounds.

Contribution

It provides the first theoretical analysis of a BIHT-type algorithm, showing NBIHT attains optimal error decay rate up to logarithmic factors.

Findings

NBIHT achieves an approximation error of order O(1/m) up to logarithmic factors.

This error rate matches the information-theoretic lower bound.

NBIHT breaks the inverse square root error decay rate, demonstrating improved performance.

Abstract

The Binary Iterative Hard Thresholding (BIHT) algorithm is a popular reconstruction method for one-bit compressed sensing due to its simplicity and fast empirical convergence. There have been several works about BIHT but a theoretical understanding of the corresponding approximation error and convergence rate still remains open. This paper shows that the normalized version of BIHT (NBHIT) achieves an approximation error rate optimal up to logarithmic factors. More precisely, using $m$ one-bit measurements of an $s$-sparse vector $x$, we prove that the approximation error of NBIHT is of order $O \left(1 \over m \right)$ up to logarithmic factors, which matches the information-theoretic lower bound $\Omega \left(1 \over m \right)$ proved by Jacques, Laska, Boufounos, and Baraniuk in 2013. To our knowledge, this is the first theoretical analysis of a BIHT-type algorithm that explains the optimal rate of error decay empirically observed in the literature. This also makes NBIHT the first provable computationally-efficient one-bit compressed sensing algorithm that breaks the inverse square root error decay rate $O \left(1 \over m^{1/2} \right)$.