Uncertainty-Based Non-Parametric Active Peak Detection

TL;DR

This paper introduces an active, non-parametric peak detection method using an uncertainty-based sampling scheme for source localization, demonstrating superior performance with few measurements and theoretical error bounds.

Contribution

It presents a novel active peak detection algorithm with an uncertainty-based sampling scheme and provides theoretical error bounds for source localization accuracy.

Findings

Error scales as O(log^2 m/m) under mild conditions

Outperforms passive localization methods in low-sample regimes

Outperforms greedy methods in low-sample regimes

Abstract

Active, non-parametric peak detection is considered. As a use case, active source localization is examined and an uncertainty-based sampling scheme algorithm to effectively localize the peak from a few energy measurements is designed. It is shown that under very mild conditions, the source localization error with $m$ actively chosen energy measurements scales as $O(\log^2 m/m)$. Numerically, it is shown that in low-sample regimes, the proposed method enjoys superior performance on several types of data and outperforms the state-of-the-art passive source localization approaches and in the low sample regime, can outperform greedy methods as well.