4 papers
Posterior Bayesian Neural Networks with Dependent Weights
Nicola Apollonio, Giovanni Franzina, Giovanni Luca Torrisi
We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gau…
Functional Large Deviations for Wide Deep Neural Networks with Gaussian Initialization and Lipschitz Activations
Claudio Macci, Barbara Pacchiarotti, Katerina Papagiannouli +2
We establish a functional large deviation principle for fully connected multi-layer perceptrons with i.i.d. Gaussian weights (LeCun initialization) and general Lipschitz activation…
Competing bootstrap processes on the random graph
Michele Garetto, Emilio Leonardi, Giovanni Luca Torrisi
We extend classical bootstrap percolation by introducing two concurrent, competing processes on an ErdÅs--Rényi random graph . Each node can assume one of three states:…
Large and moderate deviations for Gaussian neural networks
Claudio Macci, Barbara Pacchiarotti, Giovanni Luca Torrisi
We prove large and moderate deviations for the output of Gaussian fully connected neural networks. The main achievements concern deep neural networks (i.e., when the model has more…