September, Tuesday 19th

11:00 (Shannon amphitheatre, building 660) (see location):

Carlo Lucibello

(Politecnico di Torino)

Title: Probing the energy landscape of Artificial Neural Networks


Training neural networks with discrete synapses has long been considered a challenging task even for the simplest neural architectures.
In this talk I'll present a series of results which emerged from a large-deviation analysis using tools from Statistical Physics, which show that the learning problem can be made algorithmically very simple by maximizing a "local entropy": explicitly seeking extensive regions in the space of configurations with low energy. Such regions also have some highly desirable properties, in particular very good generalization capabilities.
A class of general optimization algorithms is presented, along with numerical results in shallow and deep learning assessing their effectiveness.


C. Baldassi, C. Borgs, J. Chayes, A. Ingrosso, C. Lucibello, L. Saglietti, and R. Zecchina. "Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes", PNAS (2016)

Contact: guillaume.charpiat at

Collaborateur(s) de cette page: guillaume .
Page dernièrement modifiée le Vendredi 15 septembre 2017 12:44:58 CEST par guillaume.