9 papers
Fast Stochastic Second-Order Adagrad for Nonconvex Bound-Constrained Optimization
S. Bellavia, S. Gratton, B. Morini +1
ADAGB2, a generalization of the Adagrad algorithm for stochastic optimization is introduced, which is also applicable to bound-constrained problems and capable of using second-orde…
An objective-function-free algorithm for general smooth constrained optimization
S. Bellavia, S. Gratton, B. Morini +1
A new algorithm for smooth constrained optimization is proposed that never computes the value of the problem's objective function and that handles both equality and inequality cons…
Fully stochastic trust-region methods with Barzilai-Borwein steplengths
Stefania Bellavia, Benedetta Morini, Mahsa Yousefi
We investigate stochastic gradient methods and stochastic counterparts of the Barzilai-Borwein steplengths and their application to finite-sum minimization problems. Our proposal i…
A variable dimension sketching strategy for nonlinear least-squares
Stefania Bellavia, Greta Malaspina, Benedetta Morini
We present a stochastic inexact Gauss-Newton method for the solution of nonlinear least-squares. To reduce the computational cost with respect to the classical method, at each iter…
ATE-SG: Alternate Through the Epochs Stochastic Gradient for Multi-Task Neural Networks
Stefania Bellavia, Francesco Della Santa, Alessandra Papini
This paper introduces novel alternate training procedures for hard-parameter sharing Multi-Task Neural Networks (MTNNs). Traditional MTNN training faces challenges in managing conf…
A discrete Consensus-Based Global Optimization Method with Noisy Objective Function
Stefania Bellavia, Greta Malaspina
Consensus based optimization is a derivative-free particles-based method for the solution of global optimization problems. Several versions of the method have been proposed in the…