Moment-Based Variational Inference for Stochastic Differential Equations

Christian Wildner · Heinz Koeppl

Keywords: [ Probabilistic Methods ] [ Approximate Inference ]

[ Abstract ]
Thu 15 Apr 7:30 a.m. PDT — 9:30 a.m. PDT


Existing deterministic variational inference approaches for diffusion processes use simple proposals and target the marginal density of the posterior. We construct the variational process as a controlled version of the prior process and approximate the posterior by a set of moment functions. In combination with moment closure, the smoothing problem is reduced to a deterministic optimal control problem. Exploiting the path-wise Fisher information, we propose an optimization procedure that corresponds to a natural gradient descent in the variational parameters. Our approach allows for richer variational approximations that extend to state-dependent diffusion terms. The classical Gaussian process approximation is recovered as a special case.

Chat is not available.