Adaptive Variational Particle Filtering in Non-stationary Environments

TL;DR

This paper introduces an adaptive particle filtering method for non-stationary environments, leveraging online convex optimization techniques to improve efficiency and adaptability in sequential prediction tasks.

Contribution

It formulates a novel particle filtering algorithm based on online mirror descent, achieving optimal particle efficiency in non-stationary settings.

Findings

Achieves optimal particle efficiency in non-stationary environments

Connects particle filtering with online mirror descent algorithms

Provides a theoretically grounded adaptive filtering method

Abstract

Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-stationary environment by making connections with the online mirror descent algorithm which is known to be a universal online convex optimization algorithm. As a result of this connection, our proposed particle filtering algorithm proves to achieve optimal particle efficiency.