Search Results for author: Sebastian Zeng

Found 3 papers, 2 papers with code

Latent SDEs on Homogeneous Spaces

1 code implementation NeurIPS 2023 Sebastian Zeng, Florian Graf, Roland Kwitt

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).

Bayesian Inference Variational Inference

On Measuring Excess Capacity in Neural Networks

1 code implementation16 Feb 2022 Florian Graf, Sebastian Zeng, Bastian Rieck, Marc Niethammer, Roland Kwitt

We study the excess capacity of deep networks in the context of supervised classification.

Cannot find the paper you are looking for? You can Submit a new open access paper.