Publications (10)
Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II
Yossi Arjevani, Michael Field
We study the optimization problem associated with fitting two-layer ReLU neural networks with respect to the squared loss, where labels are generated by a target network. We make u…
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry
Yossi Arjevani, Michael Field
We consider the optimization problem associated with fitting two-layers ReLU networks with respect to the squared loss, where labels are generated by a target network. We leverage…
Symmetry & critical points for a model shallow neural network
Yossi Arjevani, Michael Field
We consider the optimization problem associated with fitting two-layer ReLU networks with hidden neurons, where labels are assumed to be generated by a (teacher) neural network…
Asynchronous Networks and Event Driven Dynamics
Christian Bick, Michael Field
Real-world networks in technology, engineering and biology often exhibit dynamics that cannot be adequately reproduced using network models given by smooth dynamical systems and a…
Asynchronous Networks: Modularization of Dynamics Theorem
Christian Bick, Michael Field
Building on the first part of this paper, we develop the theory of functional asynchronous networks. We show that a large class of functional asynchronous networks can be (uniquely…
Equivariant bifurcation, quadratic equivariants, and symmetry breaking for the standard representation of
Yossi Arjevani, Michael Field
Motivated by questions originating from the study of a class of shallow student-teacher neural networks, methods are developed for the analysis of spurious minima in classes of gra…