activity
20212026
most citedA Robust Initialization of Residual Blocks for Effective ResNet Training without Batch Normalization

7 citations · 10 across the 6 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

math.OC2026

Fully Convergent Projection-based Methods with Momentum under Nonconvex Geometric Constraints

Matteo Lapucci, Diego Scuppa

Nonlinear optimization problems with complicated, nonconvex, yet geometrically structured constraints can be tackled by projected-gradient methods: under weak regularity assumption…

math.OC2026

Projected Gradient Methods with Momentum

Matteo Lapucci, Giampaolo Liuzzi, Stefano Lucidi +2

We focus on the optimization problem with smooth, possibly nonconvex objectives and a convex constraint set for which the Euclidean projection operation is practically available. F…