5 papers
A linesearch-based derivative-free method for noisy black-box problems
Alberto De Santis, Giampaolo Liuzzi, Stefano Lucidi
In this work we consider unconstrained optimization problems. The objective function is known through a zeroth order stochastic oracle that gives an estimate of the true objective…
On the Batch Size Selection in Stochastic Gradient Methods Using No-Replacement Sampling
Marco Boresta, Alberto De Santis, Stefano Lucidi
Recent stochastic gradient methods that have appeared in the literature base their efficiency and global convergence properties on a suitable control of the variance of the gradien…
Avoiding local minima in multilayer network optimization by incremental training
Alberto De Santis, Giampaolo Liuzzi, Stefano Lucidi +1
Training a large multilayer neural network can present many difficulties due to the large number of useless stationary points. These points usually attract the minimization algorit…
Mixed Finite Differences Scheme for Gradient Approximation
Marco Boresta, Tommaso Colombo, Alberto De Santis +1
In this paper we focus on the linear functionals defining an approximate version of the gradient of a function. These functionals are often used when dealing with optimization prob…
Post-transcriptional Regulation Drives Temporal Compartmentalization of the Yeast Metabolic Cycle
Maria Concetta Palumbo, Lorenzo Farina, Alberto De Santis +4
The maintainance of a stable periodicity during the yeast metabolic cycle involving approximately half of the genome requires a very strict and efficient control of gene expression…