These pages are under construction but will contain data sets for the paper Symmetry and critical points for a model shallow neural network
as well as more detailed information on the research.
Recent articles
(For a more up to date list, go to Recent publications)
- Y Arjevani and M J Field, On the principle of least symmetry breaking in shallow relu Models (arXiv preprint arXiv:1912.11939, 2019).
- Y Arjevani and M J Field, Analytic Characterization of the Hessian in Shallow ReLu Models: A Tale of Symmetry, Neurips 2020, to appear (arXiv preprint arXiv:2008.01805).
- Y Arjevani and M J Field, Symmetry and critical points for a model shallow neural network, Physica D, to appear (arXiv preprint arXiv:2003.10576v4, 2020). Data sets for critical points of types A, I and II
(Critical points in the range k = d = 3 to 20000 for type II, k = d =4 to 10000 for types A and I).
- Y Arjevani, J Bruna, M J Field, J Kileel, M Trager, and F Williams. Symmetry Breaking in Symmetric Tensor Decomposition
(arXiv preprint arXiv:2103.06234, 2021).
- Y Arjevani and M J Field, Equivariant bifurcation, quadratic equivariants, and symmetry breaking for the standard representation of Sn (arXiv preprint arXiv:2107.02422, 2021).
- Y Arjevani and M J Field, Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks (arXiv preprint arXiv:2107.10370, 2021).
email: mikefield@gmail.com
Professor Mike Field
Department of Mechanical Engineering
University of California
Santa Barbara, CA 93106
|