24 citations · 49 across the 15 of their papers we have counts for
15 papers · 1 filter
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…
Gaussian Approximation and Moderate Deviations of Poisson Shot Noises with Application to Compound Generalized Hawkes Processes
Mahmoud Khabou, Giovanni Luca Torrisi
In this article, we give explicit bounds on the Wasserstein and the Kolmogorov distances between random variables lying in the first chaos of the Poisson space and the standard Nor…
Competing bootstrap processes on the random graph
Michele Garetto, Emilio Leonardi, Giovanni Luca Torrisi
We introduce and analyze a competitive extension of classical bootstrap percolation on the Erdős--Rényi random graph . Nodes can be red, black, or white, with red and bla…
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…
Normal approximation of Random Gaussian Neural Networks
Nicola Apollonio, Daniela De Canditiis, Giovanni Franzina +2
In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results conc…
Bootstrap percolation on the stochastic block model
Giovanni Luca Torrisi, Michele Garetto, Emilio Leonardi
We analyze the bootstrap percolation process on the stochastic block model (SBM), a natural extension of the Erdős--Rényi random graph that incorporates the community structure obs…