← Search

Gabriele Perugini

2 accepted papers

2022

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry

ICML 2022spotlight

We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of parameters. Grouping classifiers into equivalence classes, we develop a standardized parameterization in which all symmetries…

Cited by 32SourcePDFScholar
2021

Entropic gradient descent algorithms and wide flat minima

ICLR 2021poster

The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization capabilities with respect to sharp ones. In this work we first discuss the relationship between alternative measures of fl…