Super-Resolution via Learned Predictor

TL;DR

This paper presents a learning-based method for high-resolution frequency estimation that predicts future measurements to improve accuracy, achieving near-complete performance with only one-third of the measurements, while maintaining interpretability.

Contribution

Introduces a novel learning-driven approach that predicts measurements to enhance frequency resolution, reducing measurement requirements without sacrificing interpretability.

Findings

Achieves high-resolution frequency estimates using only one-third of measurements.

Performance comparable to full measurement sets.

Method maintains interpretability unlike other learning-based estimators.

Abstract

Frequency estimation from measurements corrupted by noise is a fundamental challenge across numerous engineering and scientific fields. Among the pivotal factors shaping the resolution capacity of any frequency estimation technique are noise levels and measurement count. Often constrained by practical limitations, the number of measurements tends to be limited. This work introduces a learning-driven approach focused on predicting forthcoming measurements based on available samples. Subsequently, we demonstrate that we can attain high-resolution frequency estimates by combining provided and predicted measurements. In particular, our findings indicate that using just one-third of the total measurements, the method achieves a performance akin to that obtained with the complete set. Unlike existing learning-based frequency estimators, our approach's output retains full interpretability. This work holds promise for developing energy-efficient systems with reduced sampling requirements, which will benefit various applications.