Leonardo Lavagna

Leonardo Lavagna

I'm a mathematician specialized in Data Science currently pursuing a PhD in Quantum Computing

Publications

Here you can find a selection of publications. A complete list with all my scientific contributions can be found here with corresponding BibTeX entries here.

Hybrid Quantum-Classical Framework for Anomaly Detection in Time Series with QUBO formulation and QAOA

Published in 2025 International Joint Conference on Neural Networks (IJCNN), 2025

We introduce a hybrid quantum-classical framework to address anomaly detection problems in time series data using an innovative Quadratic Unconstrained Binary Optimization formulation. Code available here. Associated Blog post here Read more

Recommended citation: M. Casalbore, L. Lavagna, A. Rosato and M. Panella, "Hybrid Quantum-Classical Framework for Anomaly Detection in Time Series with QUBO formulation and QAOA," 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-8. https://ieeexplore.ieee.org/document/11228152

Novel Quantum Approaches to Hyperdimensional Computing for Neural Networks

Published in 2025 International Joint Conference on Neural Networks (IJCNN), 2025

We introduce new quantum machine learning models that combine both quantum and hyperdimensional computing. Code available here. Associated Blog post here Read more

Recommended citation: L. Lavagna, A. Ceschini, A. Rosato and M. Panella, "Novel Quantum Approaches to Hyperdimensional Computing for Neural Networks," 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-8. ieeexplore.ieee.org/document/11228152

Machine Learning-Guided microfluidic optimization of clinically inspired liposomes for nanomedicine applications

Published in International Journal of Pharmaceutics, 2025

This article discusses the transformative role of machine learning in optimizing liposome development, a process traditionally limited by its complexity, high cost, and time-intensive experimentation. By analyzing over 300 experimental conditions using a microfluidic production platform inspired by the formulations of Doxil® and Marqibo®, the study demonstrates how predictive models can efficiently determine key liposome characteristics such as particle size and polydispersity index. An open-source simulation tool was also developed to allow researchers to virtually design and test formulations, reducing the need for extensive laboratory work. The models were validated through independent experiments, confirming their robustness and adaptability. Code available here with an associated app here. Read more

Recommended citation: G. Buttitta, L. Lavagna, S. Bonacorsi, C. Barbarito, M. Moliterno, G. Saito, I. Oddone, G. Verdone, S. Raimondi, M. Panella, "Machine Learning-Guided microfluidic optimization of clinically inspired liposomes for nanomedicine applications", International Journal of Pharmaceutics, Vol. 686, 2025. https://www.sciencedirect.com/science/article/pii/S0378517325011998

On the Effects of Small Graph Perturbations in the MaxCut Problem by QAOA

Published in AVS Quantum Science, 2025

In this article we investigate the Maximum Cut (MaxCut) problem on different graph classes with the quantum approximate optimization algorithm (QAOA) using symmetries. In particular, heuristics on the relationship between graph symmetries and the approximation ratio achieved by a QAOA simulation are considered Read more

Recommended citation: L. Lavagna, S. Piperno, A. Ceschini and M. Panella, "On the Effects of Small Graph Perturbations in the MaxCut Problem by QAOA ," 2025 AVS Quantum Science 7(4), doi: 10.1116/5.0253160. https://www.researchgate.net/publication/396483291_Small_graph_perturbations_QAOA_and_the_MaxCut_problem

A topical review on time-independent perturbation theory in one-dimensional quantum systems

Published in Physica Scripta, 2025

This review presents time-independent perturbative methods for solving the one-dimensional Schrödinger equation, highlighting representative cases that reveal key aspects of the theory. The focus is on their relevance to quantum computing applications, particularly in systems with finite-dimensional state spaces. Blog post here and code here. There is also an app in the Applets page. Read more

Recommended citation: L. Lavagna, S. Carillo and M. Panella, "A topical review on time-independent perturbation theory in one-dimensional quantum systems," 2025 Phys. Scr. 100 102001. https://iopscience.iop.org/article/10.1088/1402-4896/ae0a8f

Trade-offs in Cryptosystems by Boolean and Quantum Circuits

Published in 2025 IEEE International Symposium on Circuits and Systems (ISCAS), 2025

This work explores the impact of NISQ devices on encryption-decryption schemes and has its companion blog post here and code in this repository. Read more

Recommended citation: L. Lavagna, F. De Falco, A. Ceschini, A. Rosato and M. Panella, "Trade-offs in Cryptosystems by Boolean and Quantum Circuits," 2025 IEEE International Symposium on Circuits and Systems (ISCAS), London, UK, pp. 1-5. https://ieeexplore.ieee.org/document/11043205

Evolving Hybrid Quantum-Classical GRU Architectures for Multivariate Time Series

Published in 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 2024

This paper is about an hybrid quantum-classical Gated Recurrent Unit used to infer information about multidimensional time series and has its companion blog post here. Read more

Recommended citation: Francesca De Falco, Leonardo Lavagna, Andrea Ceschini, Antonello Rosato, Massimo Panella: Evolving Hybrid Quantum-Classical GRU Architectures for Multivariate Time Series, in the 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP). https://inspirehep.net/literature/2849278

A Layerwise-Multi-Angle Approach to Fine-Tuning the Quantum Approximate Optimization Algorithm

Published in 2024 International Joint Conference on Neural Networks (IJCNN), 2024

This work was the natural development of my master thesis on quantum optimization and has its companion blog post here. Read more

Recommended citation: L. Lavagna, A. Ceschini, A. Rosato and M. Panella, "A Layerwise-Multi-Angle Approach to Fine-Tuning the Quantum Approximate Optimization Algorithm," 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 2024, pp. 1-8. https://ieeexplore.ieee.org/document/10650075