Parameter Learning and Change Detection Using a Particle Filter With Accelerated Adaptation

TL;DR

This paper introduces an enhanced particle filter inspired by genetic algorithms that rapidly adapts to parameter changes and distinguishes between regime shifts and stochastic volatility in online filtering.

Contribution

It proposes a novel particle filter with accelerated adaptation capabilities for online parameter change detection, inspired by genetic algorithms.

Findings

Achieves rapid adaptation to regime shifts

Provides a heuristic to differentiate regime shifts from stochastic volatility

Effective in online sequential filtering scenarios

Abstract

This paper presents the construction of a particle filter, which incorporates elements inspired by genetic algorithms, in order to achieve accelerated adaptation of the estimated posterior distribution to changes in model parameters. Specifically, the filter is designed for the situation where the subsequent data in online sequential filtering does not match the model posterior filtered based on data up to a current point in time. The examples considered encompass parameter regime shifts and stochastic volatility. The filter adapts to regime shifts extremely rapidly and delivers a clear heuristic for distinguishing between regime shifts and stochastic volatility, even though the model dynamics assumed by the filter exhibit neither of those features.