Gradient Boosted Filters For Signal Processing

TL;DR

This paper introduces gradient boosted filters using Hammerstein systems for dynamic signal processing, extending the success of gradient boosted models from static data to time-varying signals with theoretical and practical validation.

Contribution

It presents a novel approach replacing decision trees with Hammerstein systems in gradient boosting for signal processing, supported by theoretical analysis and demonstration.

Findings

Effective generalization to dynamic data demonstrated

Theoretical connection to Volterra series established

Potential for improved signal processing applications

Abstract

Gradient boosted decision trees have achieved remarkable success in several domains, particularly those that work with static tabular data. However, the application of gradient boosted models to signal processing is underexplored. In this work, we introduce gradient boosted filters for dynamic data, by employing Hammerstein systems in place of decision trees. We discuss the relationship of our approach to the Volterra series, providing the theoretical underpinning for its application. We demonstrate the effective generalizability of our approach with examples.