no code implementations • 20 Jul 2021 • Amil Merchant, Luke Metz, Sam Schoenholz, Ekin Dogus Cubuk
Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design.
no code implementations • 14 Oct 2020 • Atish Agarwala, Jeffrey Pennington, Yann Dauphin, Sam Schoenholz
In this work we develop a theory of early learning for models trained with softmax-cross-entropy loss and show that the learning dynamics depend crucially on the inverse-temperature $\beta$ as well as the magnitude of the logits at initialization, $||\beta{\bf z}||_{2}$.
no code implementations • 25 Sep 2019 • Lechao Xiao, Jeffrey Pennington, Sam Schoenholz
In this paper, we discuss these challenging issues in the context of wide neural networks at large depths where we will see that the situation simplifies considerably.