← Search

Leonardo Petrini

2 accepted papers

2022

Learning sparse features can lead to overfitting in neural networks

NeurIPS 2022accept

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge: for example, it is beneficial for modern architectures train…

2021

Relative stability toward diffeomorphisms indicates performance in deep nets

NeurIPS 2021poster

Understanding why deep nets can classify data in large dimensions remains a challenge. It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empirical measurements support that it is often not the case. We revisit this question by defining a maximum-entropy distrib…

Cited by 16SourcePDFScholar