Searcharxiv⌕ Search

arXiv subjects

Roberto Bellotti

Publications and source records attributed to Roberto Bellotti.

14 recordsLinked to original sources
arXiv2026

Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations

A quantum-inspired tensor network framework for wildfire susceptibility classification in the Gargano region is introduced, leveraging AlphaEarth embeddings and Matrix Product State models. The approach combines scalable geospatial representations with an interpretable quantum mask, enabling both binary and multiclass classification of wildfire susceptibility. Beyond predictive performance, the study reveals a pronounced grokking transition in the binary case and provides a detailed analysis of inter-class confusion in the multiclass setting. By introducing level-resolved mixedness diagnostics based on reduced density matrices, we show that the MPS classifier naturally encodes a hierarchy of class distinguishability, with non-adjacent categories becoming more separable than neighboring ones. These results demonstrate that tensor network models not only achieve competitive classification accuracy but also offer a physically grounded framework to quantify and interpret class separability in complex environmental datasets.

physics.soc-ph↗
arXiv2026

A Tensor Network Framework for Interpretable Graph Analysis of Brain Networks

Identifying robust neurobiological signatures of brain disorders requires machine learning approaches that combine predictive performance with interpretable representations of feature interactions. Here we introduce a quantum-inspired framework based on tensor network machine learning that learns distributed representations of gray-matter features encoded in a Matrix Product State representation, a variational ansatz originally developed for quantum many-body systems. The trained model is then used not only as a classifier but to extract quantum connected correlations between features, which encode higher-order feature interactions and which we map onto a weighted graph. This construction allows us to track, within a single representation, both: (i) the global spectral properties of the network (capturing collective learning dynamics), and (ii) node-level centrality measures (providing interpretable signatures of individual brain regions). Using repeated train-test sampling schemes, we analyze two classification tasks on structural MRI data as examples of complex brain disorders: healthy controls versus schizophrenia and versus bipolar disorder. Node-level analysis identifies a stable set of gray-matter features, most prominently Heschl gyrus, insular cortex, and frontal regions, that act as hubs across multiple centrality measures and across resamplings. These centralities display lower variability across resamplings than Shapley values, supporting the interpretive value of the network representation. The bipolar feature set emerges as a subset of the schizophrenia one, consistent with the hierarchically organized neuroanatomical alterations reported in neuroimaging studies and offering a network-based characterization of this hierarchy.

q-bio.NC↗
arXiv2025

Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems

Quantum-enhanced machine learning, encompassing both quantum algorithms and quantum-inspired classical methods such as tensor networks, offers promising tools for extracting structure from complex, high-dimensional data. In this work, we study the training dynamics of Matrix Product State (MPS) classifiers applied to three-class problems, using both fashion MNIST and hyper-spectral satellite imagery as representative datasets. We investigate the phenomenon of grokking, where generalization emerges suddenly after memorization, by tracking entanglement entropy, local magnetization, and model performance across training sweeps. Additionally, we employ information theory tools to gain deeper insights: transfer entropy is used to reveal causal dependencies between label-specific quantum masks, while O-information captures the shift from synergistic to redundant correlations among class outputs. Our results show that grokking in the fashion MNIST task coincides with a sharp entanglement transition and a peak in redundant information, whereas the overfitted hyper-spectral model retains synergistic, disordered behavior. These findings highlight the relevance of high-order information dynamics in quantum-inspired learning and emphasize the distinct learning behaviors that emerge in multi-class classification, offering a principled framework to interpret generalization in quantum machine learning architectures.

quant-ph↗
arXiv2025

The Extreme Universe Observatory on a Super-Pressure Balloon II: Mission, Payload, and Flight

The Extreme Universe Space Observatory on a Super Pressure Balloon 2 (EUSO-SPB2) is a pathfinder mission toward a space-based observatory such as the Probe of Extreme Multi-Messenger Astrophysics (POEMMA). The aim of POEMMA is the observation of Ultra High Energy COsmic Rays (UHECRs) in order to elucidate their nature and origins and to discover $\gtrsim$ 20 PeV very high energy neutrinos that originate from transient and steady astrophysical sources. EUSO-SPB2 was launched from W\=anaka New Zealand on May 13th, 2023 as a NASA Balloon Program Office test flight. The mission goals included making the first near-space altitude observations of the fluorescence emission from UHECR-induced extensive air showers (EASs) and making the first direct Cherenkov light emission from PeV cosmic rays traversing Earth's atmosphere. In addition, a Target of Opportunity program was developed for selecting and scheduling observations of potential neutrino sources as they passed just below the Earth's limb. Although a leaky balloon forced termination over the Pacific Ocean after 37 hours, data was collected to demonstrate the successful commissioning and operation of the instruments. This paper includes a description of the payload and the key instruments, pre-flight instrument characterizations in the lab and in the desert, flight operations and examples of the data collected. The flight was too short to catch a UHECR event via fluorescence, however about 10 candidate EAS events from cosmic rays were recorded via Cherenkov light.

astro-ph.HE↗
arXiv2025

Grokking as an entanglement transition in tensor network machine learning

Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired machine learning framework based on tensor networks, we numerically prove that grokking phenomenon can be related to an entanglement dynamical transition in the underlying quantum many-body systems, consisting in a one-dimensional lattice with each site hosting a qubit. Two datasets are considered as use case scenarios, namely fashion MNIST and gene expression communities of hepatocellular carcinoma. In both cases, we train Matrix Product State (MPS) to perform binary classification tasks, and we analyse the learning dynamics. We exploit measurement of qubits magnetization and correlation functions in the MPS network as a tool to identify meaningful and relevant gene subcommunities, verified by means of enrichment procedures.

quant-ph↗
arXiv2022

Planck Formula for the Gluon Parton Distribution in the Proton

We describe the gluon parton distribution function (PDF) in the proton, deduced by data from the ATLAS and HERA experiments, in the framework of the parton statistical model. The best fit parameters involved in the Planck formula that describes the gluon distribution are consistent with the results obtained from analysis of deep inelastic scattering processes. Remarkably, the agreement between the statistical model and the experimental gluon distributions is found with the same value of the "temperature" parameter $\bar{x}$ found by fitting the valence parton distributions from deep inelastic scattering. This result corroborates the validity of the statistical approach in the gluon sector.

hep-ph↗
arXiv2021

Mind the gap in university rankings: a complex network approach towards fairness

University rankings are increasingly adopted for academic comparison and success quantification, even to establish performance-based criteria for funding assignment. However, rankings are not neutral tools, and their use frequently overlooks disparities in the starting conditions of institutions. In this research, we detect and measure structural biases that affect in inhomogeneous ways the ranking outcomes of universities from diversified territorial and educational contexts. Moreover, we develop a fairer rating system based on a fully data-driven debiasing strategy that returns an equity-oriented redefinition of the achieved scores. The key idea consists in partitioning universities in similarity groups, determined from multifaceted data using complex network analysis, and referring the performance of each institution to an expectation based on its peers. Significant evidence of territorial biases emerges for official rankings concerning both the OECD and Italian university systems, hence debiasing provides relevant insights suggesting the design of fairer strategies for performance-based funding allocations.

physics.soc-ph↗
arXiv2020

Potential energy of complex networks: a novel perspective

We present a novel characterization of complex networks, based on the potential of an associated Schrödinger equation. The potential is designed so that the energy spectrum of the Schrödinger equation coincides with the graph spectrum of the normalized Laplacian. Crucial information is retained in the reconstructed potential, which provides a compact representation of the properties of the network structure. The median potential over several random network realizations is fitted via a Landau-like function, and its length scale is found to diverge as the critical connection probability is approached from above. The ruggedness of the median potential profile is quantified using the Higuchi fractal dimension, which displays a maximum at the critical connection probability. This demonstrates that this technique can be successfully employed in the study of random networks, as an alternative indicator of the percolation phase transition. We apply the proposed approach to the investigation of real-world networks describing infrastructures (US power grid). Curiously, although no notion of phase transition can be given for such networks, the fractality of the median potential displays signatures of criticality. We also show that standard techniques (such as the scaling features of the largest connected component) do not detect any signature or remnant of criticality.

physics.soc-ph↗
arXiv2017

Brain structural connectivity atrophy in Alzheimer's disease

Analysis and quantification of brain structural changes, using Magnetic resonance imaging (MRI), are increasingly used to define novel biomarkers of brain pathologies, such as Alzheimer's disease (AD). Network-based models of the brain have shown that both local and global topological properties can reveal patterns of disease propagation. On the other hand, intra-subject descriptions cannot exploit the whole information context, accessible through inter-subject comparisons. To address this, we developed a novel approach, which models brain structural connectivity atrophy with a multiplex network and summarizes it within a classification score. On an independent dataset multiplex networks were able to correctly segregate, from normal controls (NC), AD patients and subjects with mild cognitive impairment that will convert to AD (cMCI) with an accuracy of, respectively, $0.86 \pm 0.01$ and $0.84 \pm 0.01$. The model also shows that illness effects are maximally detected by parceling the brain in equal volumes of $3000$ $mm^3$ ("patches"), without any $a$ $priori$ segmentation based on anatomical features. A direct comparison to standard voxel-based morphometry on the same dataset showed that the multiplex network approach had higher sensitivity. This method is general and can have twofold potential applications: providing a reliable tool for clinical trials and a disease signature of neurodegenerative pathologies.

physics.med-ph↗
arXiv2015

Complex networks and public funding: the case of the 2007-2013 Italian program

In this paper we apply techniques of complex network analysis to data sources representing public funding programs and discuss the importance of the considered indicators for program evaluation. Starting from the Open Data repository of the 2007-2013 Italian Program Programma Operativo Nazionale 'Ricerca e Competitività' (PON R&C), we build a set of data models and perform network analysis over them. We discuss the obtained experimental results outlining interesting new perspectives that emerge from the application of the proposed methods to the socio-economical evaluation of funded programs.

physics.soc-ph↗
arXiv2015

Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation

Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic Resonance Imaging (MRI) scans can show these variations and therefore be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach, for each voxel a number of local features were calculated. In this paper we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) Sequential Forward Selection and (iii) Sequential Backward Elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on an independent set of 25 subjects. The resulting segmentations were compared with manual reference labelling. By using only 23 features for each voxel (sequential backward elimination) we obtained comparable state of-the-art performances with respect to the standard tool FreeSurfer.

physics.med-ph↗
arXiv2012

A Dynamical Approach to Operational Risk Measurement

We propose a dynamical model for the estimation of Operational Risk in banking institutions. Operational Risk is the risk that a financial loss occurs as the result of failed processes. Examples of operational losses are the ones generated by internal frauds, human errors or failed transactions. In order to encompass the most heterogeneous set of processes, in our approach the losses of each process are generated by the interplay among random noise, interactions with other processes and the efforts the bank makes to avoid losses. We show how some relevant parameters of the model can be estimated from a database of historical operational losses, validate the estimation procedure and test the forecasting power of the model. Some advantages of our approach over the traditional statistical techniques are that it allows to follow the whole time evolution of the losses and to take into account different-time correlations among the processes.

q-fin.RM↗
arXiv2012

A Dynamical Model for Forecasting Operational Losses

A novel dynamical model for the study of operational risk in banks and suitable for the calculation of the Value at Risk (VaR) is proposed. The equation of motion takes into account the interactions among different bank's processes, the spontaneous generation of losses via a noise term and the efforts made by the bank to avoid their occurrence. Since the model is very general, it can be tailored on the internal organizational structure of a specific bank by estimating some of its parameters from historical operational losses. The model is exactly solved in the case in which there are no causal loops in the matrix of couplings and it is shown how the solution can be exploited to estimate also the parameters of the noise. The forecasting power of the model is investigated by using a fraction $f$ of simulated data to estimate the parameters, showing that for $f = 0.75$ the VaR can be forecast with an error $\simeq 10^{-3}$.

q-fin.RM↗