no code implementations • 2 May 2024 • Han Wang, Eiji Kawasaki, Guillaume Damblin, Geoffrey Daniel
We present new Bayesian Last Layer models in the setting of multivariate regression under heteroscedastic noise, and propose an optimization algorithm for parameter learning.
1 code implementation • 17 Oct 2022 • Eiji Kawasaki, Markus Holzmann
Since it requires the computation of a so-called "noise penalty" determined by the variance of the training loss function over the mini-batches, we refer to this data subsampling strategy as Penalty Bayesian Neural Networks - PBNNs.
1 code implementation • 4 Apr 2022 • Elouan Argouarc'h, François Desbouvries, Eric Barat, Eiji Kawasaki, Thomas Dautremer
In this paper we propose Discretely Indexed flows (DIF) as a new tool for solving variational estimation problems.