paper-with-me

Papers

Natural Gradient Bayesian Filtering: Geometry-Aware Filter for Dynamical Systems

2026-05-04 · Chang Liu, Wenhan Cao, Zeju Sun, Tianyi Zhang, Jiayu Yuan, Yi Zeng, Ting Yuan, Yao Lyu, Wei Wu, Stephen Shing-Toung Yau, Shengbo Eben Li arxiv

Bayesian filtering is a cornerstone of state estimation in complex systems such as aerospace systems, yet exact solutions are available only for linear Gaussian models. In practice,nonlinear systems are handled through tractable approximations,with Gaussian filters such as the extended and unscented Kalman filters being among the most widely used methods. This tutorial revisits Gaussian filtering from an information-geometric perspective, viewing the prediction and measurement update steps as inference procedures over state distributions. Within this framework, we introduce a geometry-aware Gaussian filtering approach that leverages natural gradient descent on the statistical manifold of Gaussian distributions. The resulting Natural Gradient Gaussian Approximation (NANO) filter iteratively refines the posterior mean and covariance while respecting the intrinsic geometry of the Gaussian family and preserving the positive definiteness of the covariance matrix. We further highlight fundamental connections to the classical Kalman filtering, showing that a single natural-gradient step exactly recovers the Kalman measurement update in the linear-Gaussian case. The practical implications of the proposed framework are illustrated through case studies in representative nonlinear estimation problems,including satellite attitude estimation, simultaneous localization and mapping, and state estimation for robotic systems including quadruped and humanoid robots.

📄 PDF Abstract BibTeX arXiv:2605.02306

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A unified theory of adaptive stochastic gradient descent as Bayesian filtering

2019-05-01 · ICLR 2019 5 · Laurence Aitchison

We formulate stochastic gradient descent (SGD) as a novel factorised Bayesian filtering problem, in which each parameter is inferred separately, conditioned on the corresopnding backpropagated gradient. Inference in thi…

General Classification

On the Locality of the Natural Gradient for Deep Learning

2020-05-21 · Nihat Ay

We study the natural gradient method for learning in deep Bayesian networks, including neural networks. There are two natural geometries associated with such learning systems consisting of visible and hidden units. One g…

Deep Learning

Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models

2018-07-12 · Mohammad Emtiyaz Khan, Didrik Nielsen

Bayesian inference plays an important role in advancing machine learning, but faces computational challenges when applied to complex models such as deep neural networks. Variational inference circumvents these challenges…

Bayesian InferenceVariational Inference

Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods

2018-07-19 · NeurIPS 2020 12 · Laurence Aitchison

We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient…

Bayesian Inference

Information Geometry of Variational Bayes

2025-09-19 · Mohammad Emtiyaz Khan arxiv

We highlight a fundamental connection between information geometry and variational Bayes (VB) and discuss its consequences for machine learning. Under certain conditions, a VB solution always requires estimation or compu…