The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space

3 January 2019

Papers citing "The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space"

12 / 12 papers shown

Title
LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models Hossein Abdi Mingfei Sun Andi Zhang Samuel Kaski Wei Pan 73 0 0 15 Oct 2024
Implicit Maximum a Posteriori Filtering via Adaptive Optimization Gianluca M Bencomo Jake C. Snell Thomas L. Griffiths 440 4 0 17 Nov 2023
Signal Processing Meets SGD: From Momentum to Filter Zhipeng Yao Guisong Chang Jiaqi Zhang Qi Zhang Dazhou Li Yu Zhang ODL 113 0 0 06 Nov 2023
A Recursive Newton Method for Smoothing in Nonlinear State Space Models F. Yaghoobi Hany Abdulsamad Simo Särkkä 27 1 0 15 Jun 2023
Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance Yifan Chen Daniel Zhengyu Huang Jiaoyang Huang Sebastian Reich Andrew M. Stuart 84 19 0 21 Feb 2023
Kalman filters as the steady-state solution of gradient descent on variational free energy M. Baltieri Takuya Isomura 61 6 0 20 Nov 2021
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity A. Davtyan Sepehr Sameni L. Cerkezi Givi Meishvili Adam Bielski Paolo Favaro ODL 176 3 0 07 Jul 2021
Applications of the Free Energy Principle to Machine Learning and Neuroscience Beren Millidge DRL 117 8 0 30 Jun 2021
Information-geometry of physics-informed statistical manifolds and its use in data assimilation F. Boso D. Tartakovsky AI4CE 81 8 0 01 Mar 2021
Predictive Coding Approximates Backprop along Arbitrary Computation Graphs Beren Millidge Alexander Tschantz Christopher L. Buckley 136 124 0 07 Jun 2020
TRADI: Tracking deep neural network weight distributions for uncertainty estimation Gianni Franchi Andrei Bursuc Emanuel Aldea Séverine Dubuisson Isabelle Bloch UQCV 167 52 0 24 Dec 2019
Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks Nikola B. Kovachki Andrew M. Stuart BDL 111 139 0 10 Aug 2018