Federated Learning (FL) is a distributed machine learning paradigm where clients
collaboratively train a model using their local (human-generated) datasets. While existing …

In this work, we show that neural networks can be represented via the mathematical theory
of quiver representations. More specifically, we prove that a neural network is a quiver …

It is well known that neural networks with rectified linear units (ReLU) activation functions are
positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize …

This work introduces the first toolkit around path-norms that is fully able to encompass
general DAG ReLU networks with biases, skip connections and any operation based on the …

It was empirically confirmed by Keskar et al.\cite {SharpMinima} that flatter minima
generalize better. However, for the popular ReLU network, sharp minimum can also …

Optimal a priori estimates are derived for the population risk, also known as the
generalization error, of a regularized residual network model. An important part of the …

Rectified linear unit (ReLU), as a non-linear activation function, is well known to improve the
expressivity of neural networks such that any continuous function can be approximated to …