A Geometric View of Functional Spaces of Neural Networks

  • Matthew Trager (Amazon US)
Live Stream


In this talk, I will present some of my work on the functional space associated with neural networks. I will focus on simple classes of networks, including feedforward networks with linear and polynomial activations and two-layer ReLU networks, that provide a tractable setting where many geometric properties of general networks can be studied in detail. In particular, I will emphasize the distinction between the intrinsic function space and its parameterization, in order to shed light on the impact of the architecture on the expressivity of a model and on the corresponding optimization landscapes.

Work done outside Amazon.

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