activity
20232026
most citedConvergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models

1 citations · 2 across the 8 of their papers we have counts for

collaborators
Showing 2024Show all

5 papers · 1 filter

cs.RO2024

Optimization-Driven Design of Monolithic Soft-Rigid Grippers

Pierluigi Mansueto, Mihai Dragusanu, Anjum Saeed +3

Sim-to-real transfer remains a significant challenge in soft robotics due to the unpredictability introduced by common manufacturing processes such as 3D printing and molding. Thes…

math.OC2024

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems

Matteo Lapucci, Davide Pucci

In this work, we address unconstrained finite-sum optimization problems, with particular focus on instances originating in large scale deep learning scenarios. Our main interest li…

math.OC20241 cited

Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models

Matteo Lapucci, Davide Pucci

In this paper, we deal with algorithms to solve the finite-sum problems related to fitting over-parametrized models, that typically satisfy the interpolation condition. In particul…

math.OC2024

Combining Gradient Information and Primitive Directions for High-Performance Mixed-Integer Optimization

Matteo Lapucci, Giampaolo Liuzzi, Stefano Lucidi +1

In this paper we consider bound-constrained mixed-integer optimization problems where the objective function is differentiable w.r.t.\ the continuous variables for every configurat…

math.OC2024

Effective Front-Descent Algorithms with Convergence Guarantees

Matteo Lapucci, Pierluigi Mansueto, Davide Pucci

In this manuscript, we address continuous unconstrained multi-objective optimization problems and we discuss descent type methods for the reconstruction of the Pareto set. Specific…