Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

2021/02/15 by Adrien Corenflos, Corenflos, Adrien, Jim Thornton +6 · 6 citations
Computer Science · Mathematics · #Computation (stat.CO) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Target Tracking and Data Fusion in Sensor Networks

paper · pdf · doi:10.48550/arxiv.2102.07850

openalex publication_date 2021/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF, necessary to obtain low variance likelihood and states estimates. However, traditional resampling methods result in PF-based loss functions being non-differentiable with respect to model and PF parameters. In a variational inference context, resampling also yields high variance gradient estimates of the PF-based evidence lower bound. By leveraging optimal transport ideas, we introduce a principled differentiable particle filter and provide convergence results. We demonstrate this novel method on a variety of applications.

Cited by

• Diffusion differentiable resampling
• KALIKO: Kalman-Implicit Koopman Operator Learning For Prediction of Nonlinear Dynamical Systems
• pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements
• PyDPF: A Python Package for Differentiable Particle Filtering
• DKFNet: Differentiable Kalman Filter for Field Inversion and Machine Learning
• Differentiable Adaptive Kalman Filtering via Optimal Transport

Related

• Differentiable Particle Filtering using Optimal Placement Resampling
• Variational Marginal Particle Filters
• Normalizing Flow-based Differentiable Particle Filters
• Optimal Transport Particle Filters
• Differentiable Particle Filters: End-to-End Learning with Algorithmic\n Priors