no code implementations • 27 Feb 2023 • Soumi Chaki, David Weinberg, Ayca Özcelikkale
We investigate federated learning for training multiple SNNs at clients when two mechanisms reduce the uplink communication cost: i) random masking of the model updates sent from the clients to the server; and ii) client dropouts where some clients do not send their updates to the server.
no code implementations • 6 Apr 2022 • David Bosch, Ashkan Panahi, Ayca Özcelikkale, Devdatt Dubhash
We compute precise asymptotic expressions for the learning curves of least squares random feature (RF) models with either a separable strongly convex regularization or the $\ell_1$ regularization.