CCM Colloquium / Group Meeting

CCM Seminar: David Duvenaud (U Toronto)


Title: Latent Stochastic Differential Equations: An Unexplored Model Class.

Abstract: We show how to do gradient-based stochastic variational inference in stochastic differential equations (SDEs), in a way that allows the use of adaptive SDE solvers.  This allows us to scalably fit a new family of richly-parameterized distributions over irregularly-sampled time series.  We apply latent SDEs to motion capture data, and to demonstrate infinitely-deep Bayesian neural networks.  We also discuss the pros and cons of this barely-explored model class, comparing it to Gaussian processes and neural processes.

Some technical details are in this paper:
And code is available at: