3 papers
cond-mat.dis-nn2019
Clustering of solutions in the symmetric binary perceptron
Carlo Baldassi, Riccardo Della Vecchia, Carlo Lucibello +1
The geometrical features of the (non-convex) loss landscape of neural network models are crucial in ensuring successful optimization and, most importantly, the capability to genera…
cond-mat.dis-nn2019
Generalized Approximate Survey Propagation for High-Dimensional Estimation
Luca Saglietti, Yue M. Lu, Carlo Lucibello
In Generalized Linear Estimation (GLE) problems, we seek to estimate a signal that is observed through a linear transform followed by a component-wise, possibly nonlinear and noisy…
stat.ML2019
Critical initialisation in continuous approximations of binary neural networks
George Stamatescu, Federica Gerace, Carlo Lucibello +2
The training of stochastic neural network models with binary () weights and activations via continuous surrogate networks is investigated. We derive new surrogates using a no…