2 papers
cs.AI2026
Simplifying Neural Networks During Training
Lorenzo Sciandra, Samuele Fonio, Roberto Esposito
Understanding and exploiting the training dynamics of overparameterized deep neural networks remains a central challenge in modern machine learning. Recent evidence on Neural Colla…
cs.LG2024
Supplementary Materials to Graph Convolutional Branch and Bound
Lorenzo Sciandra, Roberto Esposito, Andrea Cesare Grosso +2
This article explores the integration of deep learning models into combinatorial optimization pipelines, specifically targeting NP-hard problems. Traditional exact algorithms for s…