no code implementations • 18 Apr 2024 • Anna Shalova, André Schlichting, Mark Peletier
In this regime the set of global minimizers of the loss is large, and when initialized in a neighbourhood of this zero-loss set a noisy gradient descent algorithm slowly evolves along this set.
1 code implementation • 14 Aug 2018 • Anatoliy Babic, Harshit Bansal, Gianluca Finocchio, Julian Golak, Mark Peletier, Jim Portegies, Clara Stegehuis, Anuj Tyagi, Roland Vincze, William Weimin Yoo
After training, the Variational Autoencoders generated trajectories that are difficult to distinguish, visually, from the data.