Bayesian identification of nonseparable Hamiltonians with multiplicative noise using deep learning and reduced-order modeling

arXiv:2401.12476v2 Announce Type: replace-cross
Abstract: This paper presents a structure-preserving Bayesian approach for learning nonseparable Hamiltonian systems using stochastic dynamic models allowing for statistically-dependent, vector-valued additive and multiplicative measurement noise. The approach is comprised of three main facets. First, we derive a Gaussian filter for a statistically-dependent, vector-valued, additive and multiplicative noise model that is needed to evaluate the likelihood within the Bayesian posterior. Second, we develop a novel algorithm for cost-effective application of Bayesian system identification to high-dimensional systems. …

abstract arxiv bayesian cs.lg deep learning dynamic filter identification math.ds measurement modeling noise paper physics.data-an replace stat.co stat.ml stochastic systems type vector