[Statlist] Reminder: FDS Seminar talk with Emmanuel Abbé, EPFL Lausanne - 24 March 2022, 16:15-​17:15 CET

[Maurer Letizia]

We are pleased to announce and invite you to the next talk in our FDS seminar series

"Towards a characterization of when neural networks can learn“
by Emmanuel Abbé, EPFL Lausanne

Date and Time: Thursday, 24 March 2022, 16:15-​17:15 CET
Place: ETH Zurich, HG D 1.1

Abstract: It is currently known how to characterize functions that neural networks can learn with SGD for two extremal parametrizations: neural networks in the linear/kernel regime, and neural networks with no structural constraints. However, for the main parametrization of interest -​--non-linear but regular networks-​-- no tight characterization has yet been achieved, despite significant developments. In this talk, we take a step in this direction by considering depth-​2 neural networks trained by SGD in the mean-​field regime. We consider functions on binary inputs that depend on a latent low-​dimensional subspace, since this provides a challenging framework for linear models (curse of dimensionality) but not for neural networks that routinely tackle high-​dimensional data. Accordingly, we study learning of such functions with a linear sample complexity. In this setting, we establish a necessary and nearly sufficient condition for learning, i.e., the merged-​staircase property (MSP). Joint work with E. Boix (MIT) and T. Misiakiewicz (Stanford)


Organisers: A. Bandeira, H. Bölcskei, P. Bühlmann, F. Yang, S. van de Geer


Seminar website: https://math.ethz.ch/sfs/news-and-events/data-science-seminar.html