William Spataro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
William Spataro has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Rocco Rongo
University of Calabria
48 shared publications - Donato Dambrosio
University of Calabria
29 shared publications - Giuseppe Andrea Trunfio
Università degli Studi di Sassari
18 shared publications Salvatore Di Gregorio
University of Calabria
16 shared publications- Valeria Lupiano
National Research Council
11 shared publications Maria Vittoria Avolio
University of Calabria
9 shared publications
Latest Publications
- Open Access
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
A Hierarchical Approach forMulti-Dimensional Load Balancing in Parallel Execution of Cellular Automata
Cellular Automata play an important role in the simulation of complex systems where non-linear dynamical behaviors emerge from local interactions of their constituent parts. The spatial nature of cellular automata permits an efficient and straightforward parallelization by domain space partitioning among computing nodes. Nevertheless, load balancing issues can easily arise due to differences in computation times of the different portions of the domain space. This paper is focused on the load balancing technique applied to the parallel execution of cellular automata in the case of multi-dimensional space partitioning, i.e., when the domain space is partitioned along more than one dimension. In particular, a hierarchical approach is introduced that maximizes performances thanks to domain partitioning not constrained to a rigid grid structure. The advantages of avoiding a rigid grid structure for partitioning are due to the resulting greater degree of freedom in workload balancing and are proved by an extensive experimental evaluation.
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Hierarchical Approach forMulti-Dimensional Load Balancing in Parallel Execution of Cellular Automata
Cellular Automata play an important role in the simulation of complex systems where non-linear dynamical behaviors emerge from local interactions of their constituent parts. The spatial nature of cellular automata permits an efficient and straightforward parallelization by domain space partitioning among computing nodes. Nevertheless, load balancing issues can easily arise due to differences in computation times of the different portions of the domain space. This paper is focused on the load balancing technique applied to the parallel execution of cellular automata in the case of multi-dimensional space partitioning, i.e., when the domain space is partitioned along more than one dimension. In particular, a hierarchical approach is introduced that maximizes performances thanks to domain partitioning not constrained to a rigid grid structure. The advantages of avoiding a rigid grid structure for partitioning are due to the resulting greater degree of freedom in workload balancing and are proved by an extensive experimental evaluation.
- Open Access
- 28 July 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (1) , 77-96
An optimizer derived from Halpern’s method for enhanced neural network convergence and reduced carbon emissions
This work examines the Halpern’s iterative method as a means to create new neural network optimizers that could surpass many current existing approaches. We introduce HalpernSGD, an innovative network optimizer that leverages Halpern’s technique to enhance the rate of convergence of the Stochastic Gradient Descent (SGD), leading to reduced carbon emissions in neural network training processes. The combination of Halpern’s iterative method and Gradient Descent (GD) has led to an algorithm with a quadratic rate of convergence compared to the simple GD. Experimental comparisons between their stochastic versions show that HalpernSGD achieves greater efficiency than SGD by requiring fewer training epochs, thus reducing energy consumption and carbon footprint while maintaining model accuracy. We also compare HalpernSGD with ADAM, identifying potential improvements to ADAM’s approach in terms of stability and convergence, and suggesting a future direction for the development of combined optimizers. The implementation for HalpernSGD can be accessed at: https://github.com/EttoreRitacco/HalpernSGD.git
- 28 July 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (1) , 77-96
Open AccessAn optimizer derived from Halpern’s method for enhanced neural network convergence and reduced carbon emissions
This work examines the Halpern’s iterative method as a means to create new neural network optimizers that could surpass many current existing approaches. We introduce HalpernSGD, an innovative network optimizer that leverages Halpern’s technique to enhance the rate of convergence of the Stochastic Gradient Descent (SGD), leading to reduced carbon emissions in neural network training processes. The combination of Halpern’s iterative method and Gradient Descent (GD) has led to an algorithm with a quadratic rate of convergence compared to the simple GD. Experimental comparisons between their stochastic versions show that HalpernSGD achieves greater efficiency than SGD by requiring fewer training epochs, thus reducing energy consumption and carbon footprint while maintaining model accuracy. We also compare HalpernSGD with ADAM, identifying potential improvements to ADAM’s approach in terms of stability and convergence, and suggesting a future direction for the development of combined optimizers. The implementation for HalpernSGD can be accessed at: https://github.com/EttoreRitacco/HalpernSGD.git
- 1 January 2025
- Published by Springer Nature
- p. 362-369
Exploring Hierarchical MPI Reduction Collective Algorithms Targeted to Multicore Node Clusters
- 1 January 2025
- Published by Springer Nature
- p. 362-369
Exploring Hierarchical MPI Reduction Collective Algorithms Targeted to Multicore Node Clusters
- Open Access
- 10 January 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (8) , 9273-9287
Tailoring load balancing of cellular automata parallel execution to the case of a two-dimensional partitioned domain
In this paper, techniques for dynamic load balancing of the cellular automata parallel execution are presented for the case of domain space partitioned along two dimensions. Starting from general closed-form expressions that allow to compute the optimal workload assignment in a dynamic fashion when partitioning takes place along only one dimension, we tailor the procedure to allow partitioning and balancing along both dimensions. Both qualitative and quantitative experiments are carried out that assess performance improvement in applying load balancing for the case of two-dimensional partitioned domain, especially when the load balancing takes place along both dimensions.
- 10 January 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (8) , 9273-9287
Open AccessTailoring load balancing of cellular automata parallel execution to the case of a two-dimensional partitioned domain
In this paper, techniques for dynamic load balancing of the cellular automata parallel execution are presented for the case of domain space partitioned along two dimensions. Starting from general closed-form expressions that allow to compute the optimal workload assignment in a dynamic fashion when partitioning takes place along only one dimension, we tailor the procedure to allow partitioning and balancing along both dimensions. Both qualitative and quantitative experiments are carried out that assess performance improvement in applying load balancing for the case of two-dimensional partitioned domain, especially when the load balancing takes place along both dimensions.
- 10 January 2022
- Published by Elsevier in Journal of Computational Science
- Vol. 59
Towards efficient GPGPU Cellular Automata model implementation using persistent active cells
- 10 January 2022
- Published by Elsevier in Journal of Computational Science
- Vol. 59
Towards efficient GPGPU Cellular Automata model implementation using persistent active cells
- 1 January 2022
- Published by Springer Nature
- p. 85-96
Effectiveness of Dynamic Load Balancing in Parallel Execution of a Subsurface Flow Cellular Automata Model
- 1 January 2022
- Published by Springer Nature
- p. 85-96
Effectiveness of Dynamic Load Balancing in Parallel Execution of a Subsurface Flow Cellular Automata Model
- 1 January 2021
- Published by Elsevier in Computers & Mathematics with Applications
- Vol. 81, 133-158
OpenCAL system extension and application to the three-dimensional Richards equation for unsaturated flow
- 1 January 2021
- Published by Elsevier in Computers & Mathematics with Applications
- Vol. 81, 133-158
OpenCAL system extension and application to the three-dimensional Richards equation for unsaturated flow
- 18 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (2) , 470-484
Dynamic Load Balancing in Parallel Execution of Cellular Automata
The allocation of the computational load across different processing elements is an important issue in parallel computing. Indeed, an unbalanced load distribution can strongly affect the performances of a parallel system caused by an excess of synchronization idle times due to less loaded processes waiting for more loaded ones. In this paper, we focus on the load balancing issues in the context of the parallel execution of spatial-related applications where the domain space is partitioned in regions that are assigned to different processing elements. In particular, without loss of generality, we consider the spatial-related Cellular Automata computational paradigm for evaluating the proposed dynamic load balancing approach. The main contribution of this paper is the derivation of simple closed-form expressions that allow to compute the optimal workload assignment in a dynamic fashion, with the goal of guaranteeing a fully balanced workload distribution during the parallel execution. Based on these expressions, an algorithm for balanced execution of cellular automata is presented and implemented using the MPI technology. Eventually, an experimental section practically shows the behaviour of the proposed dynamic load balancing approach and proves its performance improvement, compared to the not-balanced version, as witnessed by the appreciable reduction of execution times.
- 18 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (2) , 470-484
Dynamic Load Balancing in Parallel Execution of Cellular Automata
The allocation of the computational load across different processing elements is an important issue in parallel computing. Indeed, an unbalanced load distribution can strongly affect the performances of a parallel system caused by an excess of synchronization idle times due to less loaded processes waiting for more loaded ones. In this paper, we focus on the load balancing issues in the context of the parallel execution of spatial-related applications where the domain space is partitioned in regions that are assigned to different processing elements. In particular, without loss of generality, we consider the spatial-related Cellular Automata computational paradigm for evaluating the proposed dynamic load balancing approach. The main contribution of this paper is the derivation of simple closed-form expressions that allow to compute the optimal workload assignment in a dynamic fashion, with the goal of guaranteeing a fully balanced workload distribution during the parallel execution. Based on these expressions, an algorithm for balanced execution of cellular automata is presented and implemented using the MPI technology. Eventually, an experimental section practically shows the behaviour of the proposed dynamic load balancing approach and proves its performance improvement, compared to the not-balanced version, as witnessed by the appreciable reduction of execution times.
- 11 July 2020
- Published by Springer Nature
- p. 66-77
Exploiting Distributed Discrete-Event Simulation Techniques for Parallel Execution of Cellular Automata
- 11 July 2020
- Published by Springer Nature
- p. 66-77
Exploiting Distributed Discrete-Event Simulation Techniques for Parallel Execution of Cellular Automata
- 14 February 2020
- Published by Springer Nature
- p. 278-290
A Dynamic Load Balancing Technique for Parallel Execution of Structured Grid Models
- 14 February 2020
- Published by Springer Nature
- p. 278-290
A Dynamic Load Balancing Technique for Parallel Execution of Structured Grid Models