On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation

1 code implementation • 22 Jan 2020 • Nicolas Brosse, Carlos Riquelme, Alice Martin, Sylvain Gelly, Éric Moulines

Uncertainty quantification for deep learning is a challenging open problem.

General Classification Representation Learning +1

The promises and pitfalls of Stochastic Gradient Langevin Dynamics

no code implementations • NeurIPS 2018 • Nicolas Brosse, Alain Durmus, Eric Moulines

As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target posterior and behaves like Stochastic Gradient Descent (SGD).