Luca Saglietti | DeepAI

AI Chat

Featured Co-authors

Lenka Zdeborová
80 publications
Adrian V. Dalca
58 publications
Enzo Tartaglione
31 publications
Negar Rostamzadeh
29 publications
Yue M. Lu
28 publications
Carlo Baldassi
21 publications
Christian Borgs
18 publications
Riccardo Zecchina
18 publications
Alessandro Laio
16 publications
Nicolo Fusi
16 publications
Stefano Sarao Mannelli
15 publications

∙ 03/02/2023

Optimal transfer protocol by incremental layer defrosting

Transfer learning is a powerful tool enabling model training with limite...

0 Federica Gerace, et al. ∙

∙ 05/31/2022

Inducing bias is simpler than you think

Machine learning may be oblivious to human bias but it is not immune to ...

0 Stefano Sarao Mannelli, et al. ∙

∙ 06/15/2021

An Analytical Theory of Curriculum Learning in Teacher-Student Networks

In humans and animals, curriculum learning – presenting data in a curate...

11 Luca Saglietti, et al. ∙

∙ 06/09/2021

Probing transfer learning with a model of synthetic correlated datasets

Transfer learning can significantly improve the sample efficiency of neu...

0 Federica Gerace, et al. ∙

∙ 12/01/2020

Solvable Model for Inheriting the Regularization through Knowledge Distillation

In recent years the empirical success of transfer learning with neural n...

0 Luca Saglietti, et al. ∙

∙ 12/09/2019

Large deviations for the perceptron model and consequences for active learning

Active learning is a branch of machine learning that deals with problems...

0 Hugo Cui, et al. ∙

∙ 05/13/2019

Generalized Approximate Survey Propagation for High-Dimensional Estimation

In Generalized Linear Estimation (GLE) problems, we seek to estimate a s...

0 Luca Saglietti, et al. ∙

∙ 10/28/2018

Gaussian Process Prior Variational Autoencoders

Variational autoencoders (VAE) are a powerful and widely-used class of m...

1 Francesco Paolo Casale, et al. ∙

∙ 10/26/2017

On the role of synaptic stochasticity in training low-precision neural networks

Stochasticity and limited precision of synaptic weights in neural networ...

0 Carlo Baldassi, et al. ∙

∙ 05/20/2016

Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes

In artificial neural networks, learning from data is a computationally d...

0 Carlo Baldassi, et al. ∙

∙ 02/12/2016

Learning may need only a few bits of synaptic precision

Learning in neural networks poses peculiar challenges when using discret...

0 Carlo Baldassi, et al. ∙

∙ 11/18/2015

Local entropy as a measure for sampling solutions in Constraint Satisfaction Problems

We introduce a novel Entropy-driven Monte Carlo (EdMC) strategy to effic...

0 Carlo Baldassi, et al. ∙

∙ 09/18/2015

Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses

We show that discrete synaptic weights can be efficiently used for learn...

0 Carlo Baldassi, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world