Loss surface of deep and wide neural networks

  • Quynh Nguyen (University Saarbruecken)
Live Stream


What are possible properties of the loss function and how they might change with the size of the network are among the fundamental questions that one could study to improve our understanding of deep learning. In this talk, I will present some results that we have obtained along this direction, including a topological analysis of sub-level sets, critical points with global optimality, and then show how to leverage this insight to get a convergence result for gradient descent.


11.07.24 22.08.24

Math Machine Learning seminar MPI MIS + UCLA

MPI for Mathematics in the Sciences Live Stream

Katharina Matschke

MPI for Mathematics in the Sciences Contact via Mail

Upcoming Events of this Seminar