works on

From the 1 of 56 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Trainable Spline Representations for Physics-Informed Learning

Giovanni Canali, Nicola Demo, Gianluigi Rozza

This work introduces Physics-Informed Splines (PI-Splines), a structured spline-based architecture for physics-informed learning. Instead of representing the solution of a differen…

cs.LG2026

Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs

Lorenzo Tomada, Federico Pichi, Gianluigi Rozza

Graph Neural Networks (GNNs) are emerging as powerful tools for nonlinear Model Order Reduction (MOR) of time-dependent parameterized Partial Differential Equations (PDEs). However…

cs.LG2026

Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects

Giuseppe Alessio D'Inverno, Zhiyuan Hu, Leo Davy +3

Information propagation characterizes how input correlations evolve across layers in deep neural networks. This framework has been well studied using mean-field theory, which assum…

cs.LG2025

BARNN: A Bayesian Autoregressive and Recurrent Neural Network

Dario Coscia, Max Welling, Nicola Demo +1

Autoregressive and recurrent networks have achieved remarkable progress across various fields, from weather forecasting to molecular generation and Large Language Models. Despite t…

cs.LG2025

Generative Adversarial Reduced Order Modelling

Dario Coscia, Nicola Demo, Gianluigi Rozza

In this work, we present GAROM, a new approach for reduced order modelling (ROM) based on generative adversarial networks (GANs). GANs have the potential to learn data distribution…