Exponential Approximation of Bandlimited Random Processes from Oversampling

TL;DR

This paper investigates the reconstruction of bandlimited random processes using oversampling, demonstrating that exponential decay of approximation error is achievable with optimal methods and practical algorithms.

Contribution

It introduces the optimal linear reconstruction method for oversampled bandlimited processes and shows exponential decay of approximation errors, along with practical algorithms.

Findings

Exponential decay of approximation error from oversampling

Optimal linear reconstruction method established

Practical algorithms with exponential approximation ability provided

Abstract

The Shannon sampling theorem for bandlimited wide sense stationary random processes was established in 1957, which and its extensions to various random processes have been widely studied since then. However, truncation of the Shannon series suffers the drawback of slow convergence. Specifically, it is well-known that the mean-square approximation error of the truncated series at $n$ points sampled at the exact Nyquist rate is of the order $O(\frac1{\sqrt{n}})$. We consider the reconstruction of bandlimited random processes from finite oversampling points, namely, the distance between consecutive points is less than the Nyquist sampling rate. The optimal deterministic linear reconstruction method and the associated intrinsic approximation error are studied. It is found that one can achieve exponentially-decaying (but not faster) approximation errors from oversampling. Two practical reconstruction methods with exponential approximation ability are also presented.