Ayca Özcelikkale

David Bosch, Ashkan Panahi, Ayca Özcelikkale et al.

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. We propose a novel multi-level application of the convex Gaussian min max theorem (CGMT) to overcome the traditional difficulty of finding computable expressions for random features models with correlated data. Our result takes the form of a computable 4-dimensional scalar optimization. In contrast to previous results, our approach does not require solving an often intractable proximal operator, which scales with the number of model parameters. Furthermore, we extend the universality results for the training and generalization errors for RF models to $\ell_1$ regularization. In particular, we demonstrate that under mild conditions, random feature models with elastic net or $\ell_1$ regularization are asymptotically equivalent to a surrogate Gaussian model with the same first and second moments. We numerically demonstrate the predictive capacity of our results, and show experimentally that the predicted test error is accurate even in the non-asymptotic regime.

Soumi Chaki, David Weinberg, Ayca Özcelikkale

Spiking Neural Networks (SNNs) are biologically inspired alternatives to conventional Artificial Neural Networks (ANNs). Despite promising preliminary results, the trade-offs in the training of SNNs in a distributed scheme are not well understood. Here, we consider SNNs in a federated learning setting where a high-quality global model is created by aggregating multiple local models from the clients without sharing any data. 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. We evaluated the performance of the SNNs using a subset of the Spiking Heidelberg digits (SHD) dataset. The results show that a trade-off between the random masking and the client drop probabilities is crucial to obtain a satisfactory performance for a fixed number of clients.