13 papers
Constraint-driven Optimization and Parametrization of Industrial NURBS Geometries via Neural Deformation Field
Federico Tamburlin, Giovanni Canali, Giuseppe Alessio D'Inverno +3
This work presents a differentiable framework for the parametrization and shape optimization of industrial CAD geometries represented by multi-patch NURBS surfaces. The method enab…
From Well-Posed Inversion to Learning Design: Physics- Informed Neural Estimation for Autonomic Regulation
Sara Nour Sadoun, Giuseppe Alessio D'Inverno, Francois Cottin +2
Learning-based and physics-informed methods are increasingly used for inverse estimation in controlled nonlinear dynamical systems. However, in many such approaches, the theoretic…
Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selection
Gabriel Masella, Giuseppe Alessio D'Inverno, Max Goldsmith +1
The process of decision-making in football is characterized by a complex interplay between spatial positioning, opponent pressure, and player intent. This work introduces a Graph N…
Surrogate models for diffusion on graphs via sparse polynomials
Giuseppe Alessio D'Inverno, Kylian Ajavon, Simone Brugiapaglia
Diffusion kernels over graphs have been widely utilized as effective tools in various applications due to their ability to accurately model the flow of information through nodes an…
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…
On Task Vectors and Gradients
Luca Zhou, Daniele Solombrino, Donato Crisostomi +4
Task arithmetic has emerged as a simple yet powerful technique for model merging, enabling the combination of multiple finetuned models into one. Despite its empirical success, a c…