Vittorio Latorre
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vittorio Latorre has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- David Yang Gao
Federation University Australia
9 shared publications - Angelo Ciccazzo
STMicroelectronics Srl
3 shared publications - Antonio Salis
Research & Innovation Division, Tiscali Italia S.p.A., 09122 Cagliari, Italy
3 shared publications - Gianluca Boanelli
Research & Innovation Division, Tiscali Italia S.p.A., 09122 Cagliari, Italy
3 shared publications - Simone Sagratella
Sapienza University of Rome
3 shared publications Angelo Ciccazzo
ST-Microeletronics
2 shared publications
Latest Publications
- Open Access
- 1 June 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (3) , 035063
Graph neural networks trained on null signal for angle reconstruction in x-ray polarimetry
Scientific real detectors often produce sparse, irregular data defined on non-Euclidean domains, where conventional convolutional neural networks (CNNs) impose geometric biases that distort physical observables. In x-ray polarimetry, such distortions can mimic polarization signals at the percent level, critically limiting measurement fidelity. We consider a framework based on graph neural networks (GNNs) for reconstructing photoelectron emission angles from Gas Pixel Detectors, operating directly on their native sparse hexagonal topology. The network is trained solely on unpolarized simulated data and integrates rotational data augmentation, ensemble averaging, and modulation-aware model selection to reduce spurious angular modulation. Despite never encountering polarized examples, the model is able to recover the overall structure of polarized signals. Compared with the classical method of moments, an analytical approach to track angle reconstruction, the proposed GNN achieves lower per-track error but yields worse performance for polarimetry, revealing a mismatch between local reconstruction accuracy and global polarimetric performance. Compared to CNN-based approaches, the framework shows competitive performance on both unpolarized and polarized reconstructions, despite being trained in a more challenging power-law energy distribution. These results position the method as a diagnostic tool to highlight the limitations and trade-offs of learning-based approaches for x-ray-polarimetry signal reconstruction.
- 1 June 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (3) , 035063
Open AccessGraph neural networks trained on null signal for angle reconstruction in x-ray polarimetry
Scientific real detectors often produce sparse, irregular data defined on non-Euclidean domains, where conventional convolutional neural networks (CNNs) impose geometric biases that distort physical observables. In x-ray polarimetry, such distortions can mimic polarization signals at the percent level, critically limiting measurement fidelity. We consider a framework based on graph neural networks (GNNs) for reconstructing photoelectron emission angles from Gas Pixel Detectors, operating directly on their native sparse hexagonal topology. The network is trained solely on unpolarized simulated data and integrates rotational data augmentation, ensemble averaging, and modulation-aware model selection to reduce spurious angular modulation. Despite never encountering polarized examples, the model is able to recover the overall structure of polarized signals. Compared with the classical method of moments, an analytical approach to track angle reconstruction, the proposed GNN achieves lower per-track error but yields worse performance for polarimetry, revealing a mismatch between local reconstruction accuracy and global polarimetric performance. Compared to CNN-based approaches, the framework shows competitive performance on both unpolarized and polarized reconstructions, despite being trained in a more challenging power-law energy distribution. These results position the method as a diagnostic tool to highlight the limitations and trade-offs of learning-based approaches for x-ray-polarimetry signal reconstruction.
- 14 February 2026
- Published by Springer Nature in Journal of Heuristics
- Vol. 32 (1) , 8
A Hybrid Genetic Search for Selective Routing with Overlapping Clusters: A Case Study in Order Picking
- 14 February 2026
- Published by Springer Nature in Journal of Heuristics
- Vol. 32 (1) , 8
A Hybrid Genetic Search for Selective Routing with Overlapping Clusters: A Case Study in Order Picking
- Open Access
Duality for Non Convex Composite Functions via the Fenchel Rockafellar Perturbation Framework
We examine the duality theory for a class of non-convex functions obtained by composing a convex function with a continuous one. Using Fenchel duality, we derive a dual problem that satisfies weak duality under general assumptions. To better understand this duality, we compare it with classical Lagrange duality by analyzing a related, yet more complex, constrained problem. We demonstrate that the newly derived stationarity conditions are equivalent to the classical Lagrange stationarity conditions for the constrained problem, as expected by the close relationship between Fenchel and Lagrange dualities. We introduce two non-convex optimization problems and prove strong duality results with their respective duals. The second problem is a constrained optimization problem whose dual is obtained through the concurrent use of the duality theory introduced in this paper and classical Lagrange duality for constrained optimization. We also report numerical tests where we solve randomly generated instances of the presented problems using an ad-hoc primal-dual potential reduction interior point method that directly exploits the global optimality conditions established in this paper. The results include a comparison with a well-known conic programming solver applied to the convex duals of the analyzed problems. The interior point method successfully reduces the duality gap close to zero, validating the proposed duality framework. The theory presented in this paper can be applied to various non-convex problems and serves as a valuable tool in the field of hidden convex optimization.
Open AccessDuality for Non Convex Composite Functions via the Fenchel Rockafellar Perturbation Framework
We examine the duality theory for a class of non-convex functions obtained by composing a convex function with a continuous one. Using Fenchel duality, we derive a dual problem that satisfies weak duality under general assumptions. To better understand this duality, we compare it with classical Lagrange duality by analyzing a related, yet more complex, constrained problem. We demonstrate that the newly derived stationarity conditions are equivalent to the classical Lagrange stationarity conditions for the constrained problem, as expected by the close relationship between Fenchel and Lagrange dualities. We introduce two non-convex optimization problems and prove strong duality results with their respective duals. The second problem is a constrained optimization problem whose dual is obtained through the concurrent use of the duality theory introduced in this paper and classical Lagrange duality for constrained optimization. We also report numerical tests where we solve randomly generated instances of the presented problems using an ad-hoc primal-dual potential reduction interior point method that directly exploits the global optimality conditions established in this paper. The results include a comparison with a well-known conic programming solver applied to the convex duals of the analyzed problems. The interior point method successfully reduces the duality gap close to zero, validating the proposed duality framework. The theory presented in this paper can be applied to various non-convex problems and serves as a valuable tool in the field of hidden convex optimization.
- Open Access
On Implicit Concave Structures in Half-Quadratic Methods for Signal Reconstruction
In this work, we introduce a new class of non-convex functions, called implicit concave functions, which are compositions of a concave function with a continuously differentiable mapping. We analyze the properties of their minimization by leveraging Fenchel conjugate theory to construct an augmented optimization problem. This reformulation yields a one-to-one correspondence between the stationary points and local minima of the original and augmented problems. Crucially, the augmented problem admits a natural variable splitting that reveals convexity with respect to at least one block, and, in some cases, leading to a biconvex structure that is more amenable to optimization. This enables the use of efficient block coordinate descent algorithms for solving otherwise non-convex problems. As a representative application, we show how this framework applies to half-quadratic regularization in signal reconstruction and image processing. We demonstrate that common edge-preserving regularizers fall within the proposed class, and that their corresponding augmented problems are biconvex and bounded from below. Our results offer both a theoretical foundation and a practical pathway for solving a broad class of structured non-convex problems.
Open AccessOn Implicit Concave Structures in Half-Quadratic Methods for Signal Reconstruction
In this work, we introduce a new class of non-convex functions, called implicit concave functions, which are compositions of a concave function with a continuously differentiable mapping. We analyze the properties of their minimization by leveraging Fenchel conjugate theory to construct an augmented optimization problem. This reformulation yields a one-to-one correspondence between the stationary points and local minima of the original and augmented problems. Crucially, the augmented problem admits a natural variable splitting that reveals convexity with respect to at least one block, and, in some cases, leading to a biconvex structure that is more amenable to optimization. This enables the use of efficient block coordinate descent algorithms for solving otherwise non-convex problems. As a representative application, we show how this framework applies to half-quadratic regularization in signal reconstruction and image processing. We demonstrate that common edge-preserving regularizers fall within the proposed class, and that their corresponding augmented problems are biconvex and bounded from below. Our results offer both a theoretical foundation and a practical pathway for solving a broad class of structured non-convex problems.
- 5 July 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 18 (4) , 1-19
An application of a two-level genetic search for the soft-clustered vehicle routing problem
- 5 July 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 18 (4) , 1-19
An application of a two-level genetic search for the soft-clustered vehicle routing problem
- Open Access
Improving Road Safety with AI: Automated Detection of Signs and Surface Damage
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which can lead to serious accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques (CNN), achieving over 90% precision and accuracy in both detection and classification of traffic signs and road surface damage. This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the CTE Molise research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as cloud computing and High-Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, for the quick detection of anomalies and the prompt organization of maintenance operations.
Open AccessImproving Road Safety with AI: Automated Detection of Signs and Surface Damage
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which can lead to serious accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques (CNN), achieving over 90% precision and accuracy in both detection and classification of traffic signs and road surface damage. This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the CTE Molise research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as cloud computing and High-Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, for the quick detection of anomalies and the prompt organization of maintenance operations.
- Open Access
- 13 February 2025
- Published by Springer Nature in Soft Computing
- Vol. 29 (3) , 1553-1566
A hybrid genetic search based approach for the generalized vehicle routing problem
This paper introduces a novel meta-heuristic for addressing a variant of the classical Capacitated Vehicle Routing Problem (CVRP) known as the Generalized Vehicle Routing Problem (GVRP). In the GVRP, nodes are organized into clusters, with the constraint that only one node from each cluster must be visited. The proposed meta-heuristic is a Hybrid Genetic Search (HGS) that leverages recent advancements in CVRP methodologies, adapting successful strategies and techniques from CVRP to the GVRP context. To evaluate the performance of the HGS meta-heuristic, we perform an extensive computational analysis on numerous benchmark instances ranging from small to large sizes. To thoroughly analyze the algorithm’s average behavior, convergence profiles over time are reported for the considered instances. Results show that the proposed algorithm achieves 174 new best solutions out of the 498 instances considered. In only six instances out of 498, the algorithm is unable to reach or improve upon the best-known solution in the literature. These results suggest that the proposed meta-heuristic has significant potential in addressing real-world generalized vehicle routing challenges. Code available at: https://github.com/vlatorre847/HGSGVRP.
- 13 February 2025
- Published by Springer Nature in Soft Computing
- Vol. 29 (3) , 1553-1566
Open AccessA hybrid genetic search based approach for the generalized vehicle routing problem
This paper introduces a novel meta-heuristic for addressing a variant of the classical Capacitated Vehicle Routing Problem (CVRP) known as the Generalized Vehicle Routing Problem (GVRP). In the GVRP, nodes are organized into clusters, with the constraint that only one node from each cluster must be visited. The proposed meta-heuristic is a Hybrid Genetic Search (HGS) that leverages recent advancements in CVRP methodologies, adapting successful strategies and techniques from CVRP to the GVRP context. To evaluate the performance of the HGS meta-heuristic, we perform an extensive computational analysis on numerous benchmark instances ranging from small to large sizes. To thoroughly analyze the algorithm’s average behavior, convergence profiles over time are reported for the considered instances. Results show that the proposed algorithm achieves 174 new best solutions out of the 498 instances considered. In only six instances out of 498, the algorithm is unable to reach or improve upon the best-known solution in the literature. These results suggest that the proposed meta-heuristic has significant potential in addressing real-world generalized vehicle routing challenges. Code available at: https://github.com/vlatorre847/HGSGVRP.
- Open Access
- 4 February 2025
- Published by MDPI AG in Preprints.org
Improving Road Safety with AI: Automated Detection of Signs and Surface Damage
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which can lead to serious accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques (CNN). This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the CTE Molise research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as Cloud computing and High Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, for the quick detection of anomalies and the prompt organization of maintenance operations.
- 4 February 2025
- Published by MDPI AG in Preprints.org
Open AccessImproving Road Safety with AI: Automated Detection of Signs and Surface Damage
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which can lead to serious accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques (CNN). This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the CTE Molise research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as Cloud computing and High Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, for the quick detection of anomalies and the prompt organization of maintenance operations.
- Open Access
Automated Road Safety: Enhancing Sign and Surface Damage Detection with AI
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which, if unaddressed, can lead to serious road accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques. This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the Casa delle Tecnologie Emergenti (House of Emergent Technologies) Molise (Molise CTE) research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as Cloud Computing and High Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, enabling quick detection of anomalies and the prompt organization of maintenance operations
Open AccessAutomated Road Safety: Enhancing Sign and Surface Damage Detection with AI
Public transportation plays a crucial role in our lives, and the road network is a vital component in the implementation of smart cities. Recent advancements in AI have enabled the development of advanced monitoring systems capable of detecting anomalies in road surfaces and road signs, which, if unaddressed, can lead to serious road accidents. This paper presents an innovative approach to enhance road safety through the detection and classification of traffic signs and road surface damage using advanced deep learning techniques. This integrated approach supports proactive maintenance strategies, improving road safety and resource allocation for the Molise region and the city of Campobasso. The resulting system, developed as part of the Casa delle Tecnologie Emergenti (House of Emergent Technologies) Molise (Molise CTE) research project funded by the Italian Minister of Economic Growth (MIMIT), leverages cutting-edge technologies such as Cloud Computing and High Performance Computing with GPU utilization. It serves as a valuable tool for municipalities, enabling quick detection of anomalies and the prompt organization of maintenance operations
- 4 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 257-261
Smart Water Management in Agriculture: a Proposal for an Optimal Scheduling Formulation of a Gravity Water Distribution System
Agriculture represents one of the most water demanding sectors and its role is central on defining water saving policies. In this work, we propose an improved approach to the irrigation scheduling problem, reducing water wastage while satisfying farmers’ demands and crops’ water needs.For water distribution system managed with on-demand distribution approach, the efficiency of irrigation relies on the ability of the network manager (i.e., gatekeeper) to guarantee a proper service, consisting in: the irrigation scheduling, the definition of the volume of water passing through the channels at a given time, and the operations on gates and sluices to make the water reach the farms. Consequently, the irrigation scheduling inefficiencies might be limited by: i) reducing the water wastage, ii) minimizing the gatekeeper work and iii) maximizing the satisfaction of the farmers’ requirements.We propose an improved mixed-integer linear optimization formulation that adds the possibility to store water in the channels and takes seepage into account. This new formulation is able to better represent the physical behavior of the water flow in the channels network, also avoiding the presence of flooding. The proposed optimization solution is embedded within a wider monitoring framework with the intent to fully exploit the availability of a complex network of models, repositories and sensors installed in the field.The resulting problem is solved by one of the most used optimization solvers (IBM ILOG Cplex) and tested on a synthetic benchmark. Furthermore, we validate the results on a digital copy of the network that performs a hydraulic simulation of the irrigation system. The scheduling is accepted if the water introduced in the system can satisfy farmers’ requests with the considered timing and does not produce flooding.
- 4 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 257-261
Smart Water Management in Agriculture: a Proposal for an Optimal Scheduling Formulation of a Gravity Water Distribution System
Agriculture represents one of the most water demanding sectors and its role is central on defining water saving policies. In this work, we propose an improved approach to the irrigation scheduling problem, reducing water wastage while satisfying farmers’ demands and crops’ water needs.For water distribution system managed with on-demand distribution approach, the efficiency of irrigation relies on the ability of the network manager (i.e., gatekeeper) to guarantee a proper service, consisting in: the irrigation scheduling, the definition of the volume of water passing through the channels at a given time, and the operations on gates and sluices to make the water reach the farms. Consequently, the irrigation scheduling inefficiencies might be limited by: i) reducing the water wastage, ii) minimizing the gatekeeper work and iii) maximizing the satisfaction of the farmers’ requirements.We propose an improved mixed-integer linear optimization formulation that adds the possibility to store water in the channels and takes seepage into account. This new formulation is able to better represent the physical behavior of the water flow in the channels network, also avoiding the presence of flooding. The proposed optimization solution is embedded within a wider monitoring framework with the intent to fully exploit the availability of a complex network of models, repositories and sensors installed in the field.The resulting problem is solved by one of the most used optimization solvers (IBM ILOG Cplex) and tested on a synthetic benchmark. Furthermore, we validate the results on a digital copy of the network that performs a hydraulic simulation of the irrigation system. The scheduling is accepted if the water introduced in the system can satisfy farmers’ requests with the considered timing and does not produce flooding.