DISA

When? Wednesday September 4th 11.30-13.00
Where? D1140, Campus Växjö.
Registration: No registration needed – just come by

We have a guest visit from Sebastian Zeng from Universität Salzburg (Austria) who will give a guest lecture with the title Latent SDEs on Homogeneous Spaces

Abstract: We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the challenges that arise when trying to learn an (almost arbitrary) latent neural SDE from data, such as efficient gradient computation, we take a step back and study a specific subclass instead. In our case, the SDE evolves on a homogeneous latent space and is induced by stochastic dynamics of the corresponding (matrix) Lie group. In learning problems, SDEs on the unit n-sphere are arguably the most relevant incarnation of this setup. Notably, for variational inference, the sphere not only facilitates using a truly uninformative prior, but we also obtain a particularly simple and intuitive expression for the Kullback-Leibler divergence between the approximate posterior and prior process in the evidence lower bound. Experiments demonstrate that a latent SDE of the proposed type can be learned efficiently by means of an existing one-step geometric Euler-Maruyama scheme. Despite restricting ourselves to a less rich class of SDEs, we achieve competitive or even state-of-the-art results on various time series interpolation/classification problems.

For more information or questions about the seminar, please contact:
– Wolfgang Bock wolfgang.bock@lnu.se or Jonas Nordqvist jonas.nordqvist@lnu.se