no code implementations • 12 Oct 2022 • 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.
no code implementations • NeurIPS 2021 • Yossi Arjevani, Michael Field
In particular, we derive analytic estimates for the loss at different minima, and prove that modulo $O(d^{-1/2})$-terms the Hessian spectrum concentrates near small positive constants, with the exception of $\Theta(d)$ eigenvalues which grow linearly with~$d$.
no code implementations • 6 Jul 2021 • 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 gradient equivariant dynamics related to neural nets.
no code implementations • 10 Mar 2021 • Yossi Arjevani, Joan Bruna, Michael Field, Joe Kileel, Matthew Trager, Francis Williams
In this note, we consider the highly nonconvex optimization problem associated with computing the rank decomposition of symmetric tensors.
no code implementations • NeurIPS 2020 • 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.
no code implementations • 23 Mar 2020 • Yossi Arjevani, Michael Field
We consider the optimization problem associated with fitting two-layer ReLU networks with $k$ hidden neurons, where labels are assumed to be generated by a (teacher) neural network.
no code implementations • 26 Dec 2019 • Yossi Arjevani, Michael Field
We consider the optimization problem associated with fitting two-layer ReLU networks with respect to the squared loss, where labels are assumed to be generated by a target network.