Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances

Shahriar Talebi · Amirhossein Taghvaei · Mehran Mesbahi

Great Hall & Hall B1+B2 (level 1) #1908
[ ] [ Project Page ]
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST


This paper examines learning the optimal filtering policy, known as the Kalman gain, for a linear system with unknown noise covariance matrices using noisy output data. The learning problem is formulated as a stochastic policy optimiza- tion problem, aiming to minimize the output prediction error. This formulation provides a direct bridge between data-driven optimal control and, its dual, op- timal filtering. Our contributions are twofold. Firstly, we conduct a thorough convergence analysis of the stochastic gradient descent algorithm, adopted for the filtering problem, accounting for biased gradients and stability constraints. Secondly, we carefully leverage a combination of tools from linear system theory and high-dimensional statistics to derive bias-variance error bounds that scale logarithmically with problem dimension, and, in contrast to subspace methods, the length of output trajectories only affects the bias term.

Chat is not available.