Learning to Bias: Machine Learning-Enhanced Particle Filters

2026-09-24

AI Summary

This study addresses the low sample efficiency and poor dimensional scalability of particle filters arising from suboptimal proposal distributions. To overcome these limitations, this work proposes the Neural Optimal Particle Filter, which approximates the optimal proposal distribution through neural network amortized learning and offline simulation-based training. By seamlessly integrating data-driven learning into classical inference frameworks, the method optimizes the standard update procedure without altering the underlying filtering objective. Evaluated on nonlinear benchmarks, the proposed approach significantly enhances both sample efficiency and posterior estimation accuracy while maintaining moderate computational overhead and asymptotic correctness.

Abstract

Sequential inference estimates latent states from noisy and incomplete observations. Particle Filters (PFs), a class of Monte Carlo methods based on importance sampling, provide a flexible framework for this task, but often suffer from poor sample efficiency and unfavorable scaling with dimension, partly due to suboptimal proposal distributions. We address these challenges by integrating learned proposals into the PF framework. We introduce Neural Optimal Particle Filters (NOPFs), which learn an amortized approximation to the optimal proposal from offline simulated one-step conditioning tuples. The learned proposal is used as a drop-in replacement in standard PF updates, with samples corrected by standard importance weights so that the method asymptotically targets the same filtering distribution under standard support and density-evaluation assumptions. Across stochastic nonlinear benchmarks of varying inference complexity, NOPFs improve sample efficiency and distributional accuracy over standard PF baselines with modest computational overhead. The approach integrates data-driven proposal learning into classical inference without altering the underlying filtering objective.

Problem

• Particle Filters
• Sequential Inference
• Proposal Distribution
• Sample Efficiency
• Latent State Estimation

Innovation

• Particle Filters
• Neural Optimal Particle Filters
• Learned Proposal Distribution
• Amortized Inference
• Importance Sampling