no code implementations • 30 May 2024 • Javier Maass Martínez, Joaquin Fontbona
When activations respect the group action, we show that, for symmetric data, DA, FA and freely-trained models obey the exact same MF dynamic, which stays in the space of WI laws and minimizes therein the population risk.
no code implementations • 28 May 2018 • Julio Backhoff-Veraguas, Joaquin Fontbona, Gonzalo Rios, Felipe Tobar
We introduce and study a novel model-selection strategy for Bayesian learning, based on optimal transport, along with its associated predictive posterior law: the Wasserstein population barycenter of the posterior law over models.