2 citations · 5 across the 7 of their papers we have counts for
7 papers
How good is PAC-Bayes at explaining generalisation?
Antoine Picard-Weibel, Eugenio Clerico, Roman Moscoviz +1
We discuss necessary conditions for a PAC-Bayes bound to provide a meaningful generalisation guarantee. Our analysis reveals that the optimal generalisation guarantee depends solel…
A note on regularised NTK dynamics with an application to PAC-Bayesian training
Eugenio Clerico, Benjamin Guedj
We establish explicit dynamics for neural networks whose training objective has a regularising term that constrains the parameters to remain close to their initial value. This keep…
Generalisation under gradient descent via deterministic PAC-Bayes
Eugenio Clerico, Tyler Farghly, George Deligiannidis +2
We establish disintegrated PAC-Bayesian generalisation bounds for models trained with gradient descent methods or continuous gradient flows. Contrary to standard practice in the PA…
Chained Generalisation Bounds
Eugenio Clerico, Amitis Shidani, George Deligiannidis +1
This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general t…
Conditionally Gaussian PAC-Bayes
Eugenio Clerico, George Deligiannidis, Arnaud Doucet
Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradie…
Wide stochastic networks: Gaussian limit and PAC-Bayesian training
Eugenio Clerico, George Deligiannidis, Arnaud Doucet
The limit of infinite width allows for substantial simplifications in the analytical study of over-parameterised neural networks. With a suitable random initialisation, an extremel…
Stable ResNet
Soufiane Hayou, Eugenio Clerico, Bobby He +3
Deep ResNet architectures have achieved state of the art performance on many tasks. While they solve the problem of gradient vanishing, they might suffer from gradient exploding as…