Find Academic Supervisors

Federica Baccini is an Assistant Professor at the Department of Computer, Control, and Management Engineering "Antonio Ruberti", Sapienza University of Rome. She is actively involved in the RSTLess research group, collaborating with Professors Fabrizio Silvestri and Irene Amerini. Her academic journey includes a PhD in Computer Science from the University of Pisa and a Master’s in Applied Mathematics from the University of Siena. Her educational background includes: PhD in Computer Science, University of Pisa, thesis: Analysis of Multiple Relations in Multilayer and Higher-Order Networks , supervised by Prof. Monica Bianchini and Dr. Filippo Geraci. Master’s Degree in Applied Mathematics, University of Siena, summa cum laude , thesis: Network analysis for the Integration of histone modification data to explain haematopoiesis . Visiting PhD student at Queen Mary University of London under Prof. Ginestra Bianconi. Federica's research is centered on the analysis of graph-structured data, particularly focusing on multilayer and higher-order networks. She investigates machine learning models for graphs, with emphasis on similarity network fusion , weighted simplicial complexes , and data integration across disciplines. Her work spans applications in biomedicine, environmental science, scientometrics, and AI security. She has published in high-impact journals such as Physical Review E , Journal of Informetrics , and Mathematics . The recent trend in her publications highlights a strong interdisciplinary approach, combining network science with machine learning to solve real-world problems in healthcare, scholarly communication, and climate systems. Her 2025 work on adversarial data poisoning shows engagement with AI security, while her medical applications (e.g., haemodialysis app, IgA nephropathy) demonstrate translational research impact. She has no listed scientific awards at this time. Federica is actively involved in academic advising and teaching, offering the course Fundamentals of Artificial Intelligence in the Bachelor's program in Mathematical Sciences for Artificial Intelligence. While specific grant details are not mentioned, her ongoing research in AI, network science, and interdisciplinary applications suggests active participation in funded projects. She is a member of the Theory of Deep Learning initiative. She is a key contributor to the RSTLess research group , where she collaborates on cutting-edge topics in deep learning and network analysis.

• Analysis of Multilayer and Higher-Order Networks
• Graph-Structured Data
• Machine Learning for Graphs
• +10 more

Stefano Berrone is a Full Professor in the Department of Mathematical Sciences "G.L. Lagrange" (DISMA) at the Polytechnic University of Turin, where he also holds key administrative roles as Vice-Rector for Quality and President of the University Quality Assurance Committee. He is a member of the Interdepartmental Center SmartData@PoliTO and the University Committee for Research, Technology Transfer and Services to the Territory. Department of Mathematical Sciences "G.L. Lagrange" (DISMA), Polytechnic University of Turin Interdepartmental Center SmartData@PoliTO - Big Data and Data Science Laboratory Scientific leadership in EU, national, and commercial research projects Teaching assignment at Turin Polytechnic University in Tashkent (2012–2014) His research lies at the intersection of numerical analysis, scientific computing, and machine learning, with a strong emphasis on the development and analysis of advanced numerical methods. He specializes in the Virtual Element Method (VEM), mesh adaptivity and generation, high-performance computing (HPC), physics-informed neural networks, and deep learning for engineering problems. His work contributes to computational engineering, data science, and sustainable development (aligned with SDGs 4, 9, and 13). He leads multiple research groups and projects focused on numerical optimization, PDE discretization on polygonal meshes, and simulation of complex physical systems. The recent publications (2023–2025) reveal a strong trend toward hybrid computational methodologies, combining classical numerical techniques like VEM with machine learning, particularly physics-informed and neural-approximated models. There is a clear focus on stabilization-free formulations, mesh optimization, and applications in energetic materials, fluid dynamics, and subsurface modeling. The work spans high-impact journals in scientific computing, computational mechanics, and algorithms. Scientific Participations and Memberships: Full Member, SIAM (Society for Industrial and Applied Mathematics) (2020–present) Full Member, Italian Society of Applied and Industrial Mathematics (2020–present) Full Member, Italian Mathematical Union (2020–present) Full Member, National Institute of Higher Mathematics - National Group for Scientific Computing (1999–present) Research Leadership and Grants: Scientific Responsible, In-Deep (EU Horizon Europe, 2024–2028) Scientific Responsible, PYGEOM (PRIN, 2023–2026) Scientific Director of Structure, SHIMMER (Clean Hydrogen JTI, 2023–2026) Scientific Director of Structure, HPC-Spoke 6 (PNRR, 2022–2025) Scientific Responsible, AdPolyMP (PRIN, 2022–2025) Scientific Responsible, Virtual Element Methods: Analysis and Applications (PRIN, 2019–2022) Scientific Responsible, IDEA (PRIN, 2013–2015) Scientific Responsible, AIRTOLYMI (Regional, 2007–2011) Scientific Responsible, Engine Health Monitoring (Commercial, 2024–2025) Advising and Doctoral Supervision: Supervising multiple PhD students in Pure and Applied Mathematics and Mathematical Sciences Member of Doctoral Colleges in Pure and Applied Mathematics at Politecnico di Torino and University of Turin (2013–2023) Key advisor in research areas including energetic materials, computational fluid dynamics, and numerical PDEs Laboratories and Research Groups: Numerical Analysis and Scientific Computing (DISMA) Interdepartmental Center SmartData@PoliTO - Big Data and Data Science Laboratory Lead in developing computational tools like HEMSim for energetic materials simulation

• Numerical Analysis
• Scientific Computing
• High-Performance Computing
• +13 more

Renato Ferrero is an Associate Professor at the Department of Control and Computer Science (DAUIN), Politecnico di Torino (Polito) , with key roles as contact person for training activities and member of the PIC4SeR Interdepartmental Center for Service Robotics . His research spans Wireless Sensor Networks (WSN) , Internet of Things (IoT) , and Environmental Monitoring , supported by competitive grants like AGRITech Spoke 6 (2022-2025) and MIUR funding (2017). He has published extensively on topics including air pollution monitoring , quantum-inspired security , and agricultural technology , with recent work focusing on deep learning for mask/respirator detection and biofertilizer analysis . As an IEEE Access Associate Editor and program committee member for conferences like COMPSAC and RFID-TA, he contributes to academic governance. His teaching includes Computer Architecture (2019-2025) and Ubiquitous Computing (2019-2021) at Polito. He advises PhD students Chiara Panico and Nicola Dilillo , with projects in Data Science , Computer Vision , and AI Life Sciences .

• Wireless sensor networks
• Internet of Things (IoT)
• Air pollution monitoring
• +11 more

Stefano Marchesiello is a Full Professor of Applied Mechanics at the Polytechnic University of Turin, Department of Mechanical and Aerospace Engineering (DIMEAS), a position he has held since 2019. His academic work spans theoretical studies, numerical applications, and experimental tests within the field of Applied Mechanics. He maintains active roles in doctoral education, serving on mechanical engineering doctoral colleges from 2013/2014 through 2024/2025, and teaches courses including Dynamics and Identification of Nonlinear Systems, Dynamics of Mechanical Systems, Vibration Mechanics, and Machine Mechanics for Aerospace Engineering. Marchesiello's research focuses on modal analysis and identification, damage diagnosis in structures and construction materials, damping systems, mechanical vibrations, and nonlinear dynamics. His primary research lines include vehicle-bridge dynamic interaction, dynamic identification techniques in linear and nonlinear fields, damage identification, vibrations of continuous systems with non-proportional damping, innovative vibration damping devices, diagnostics and monitoring of rotating systems, and pantograph-catenary dynamic interaction. His work bridges theoretical mechanics with practical engineering applications, particularly in transportation infrastructure and mechanical systems. His recent publications demonstrate a strong focus on nonlinear system identification, structural health monitoring, and vibration analysis across various mechanical and aerospace applications. Marchesiello's research shows increasing integration of machine learning techniques with traditional mechanical engineering approaches, particularly in system identification and damage detection. His work spans from fundamental nonlinear dynamics to practical applications in railway systems, rotating machinery, and structural components. Certificate of reviewing awarded by Journal of Sound and Vibration - Elsevier, Netherlands (2013) Certificate of Excellence in Reviewing - Mechanical Systems and Signal Processing 2013 awarded by Elsevier, Netherlands (2013) Marchesiello serves as Scientific Director for multiple commercial research contracts, particularly with Officina Fratelli Bertolotti SpA, focusing on vibration damping systems for railway catenaries and rotor dynamics modeling. He has led research projects from 2008 through 2023, demonstrating sustained research leadership and industry collaboration. His editorial work includes membership on the Editorial Board of SHOCK AND VIBRATION since 2018, and he has served on program committees for the International Conference on Damage Assessment of Structures (DAMAS) across multiple years. He is actively involved with the Dynamics of Mechanical Systems and Identification research group (DIMEAS), which focuses on developing advanced methods for analyzing and identifying mechanical systems with both linear and nonlinear behaviors. His research integrates computational modeling, experimental validation, and practical applications across multiple engineering domains.

• Modal analysis
• Structural damage diagnosis
• Damping systems
• +5 more

Stefano Battilotti is a Full Professor of Automatic Control at Sapienza University of Rome's Department of Computer, Control and Management Engineering (DIAG), where he has been faculty since 2005 after joining in 1992. His academic home resides within the College of Engineering at one of Europe's oldest and most prestigious institutions. Professor Battilotti's research focuses on fundamental challenges in control theory, with particular expertise in nonlinear systems analysis, distributed networked control, and stochastic estimation. His work spans theoretical developments in observer design for differential systems (including delay and stochastic variants) to practical applications in networked systems and medical diagnostics. Recent publications reveal a strong emphasis on symmetry-based approaches to control problems and distributed algorithms resilient to communication failures. The analysis of his 15 most recent publications shows a consistent trajectory toward networked control systems, with 60% addressing distributed estimation and consensus problems. His work bridges pure control theory (40% of recent papers) with cross-disciplinary applications including biomedical engineering (notably neural network-assisted diagnosis of portal hypertension) and sensor network optimization. Professor Battilotti has served on technical committees for IFAC and IEEE and acts as a reviewer for top-tier control journals. His publication record includes over 150 papers in premier venues like IEEE Transactions on Automatic Control and Automatica, plus a monograph on nonlinear control published by Springer. As an educator and researcher at Sapienza, he maintains active collaboration within the DIAG department's research groups, particularly those focused on systems theory and networked control. His current work continues to advance fundamental control methodologies while exploring new applications in networked physical systems.

• Control Theory
• Nonlinear Systems
• Networked Control Systems
• +5 more

Fabrizio Silvestri is a Full Professor at Sapienza University of Rome's Department of Computer, Automatic and Management Engineering (DIAG), where he coordinates the Ph.D. program in Data Science. He leads the RSTLess research group focusing on Robust, Safe, and Transparent Deep Learning. Research interests: Artificial Intelligence, Machine Learning, Web Search, Natural Language Processing, Information Retrieval, Graph Neural Networks Research Trends from recent publications reveal: Advancements in sequential recommendation systems using topological and sheaf-based neural networks Focus on sustainable AI through eco-aware graph neural networks Counterfactual explanations for graph models and machine unlearning Security applications in dense retrieval and data poisoning defense Time series analysis for 5G network monitoring Integration of attention mechanisms and positional encoding in Transformers Scientific Achievements : ECIR 2018 Test of Time Award 3 Best Paper Awards (ECIR 2007, IEEE WI 2004, WSDM 2011 Runner-Up) Yahoo! Patent Milestone Award Recipient of Yahoo! Labs Excellence Program (LEAP) and Faculty Research Engagement Program (FREP) Finalist for ERCIM Cor Baayen Award (2005) Academic Leadership : Holds 9 industrial patents from Yahoo! and Facebook AI. Directed Facebook AI research groups combating malicious content. Ph.D. in Computer Science from University of Pisa with thesis on High-Performance Issues in Web Search Engines . Supervises thesis projects through the RSTLess group website .

• Artificial Intelligence
• Machine Learning
• Web Search
• +7 more

Stefano Vigogna is an Associate Professor in the Department of Mathematics at the University of Rome Tor Vergata with significant contributions to theoretical machine learning. He is affiliated with the Rome Center on Mathematics for Modeling and Data Sciences (RoMaDS), focusing on the mathematical foundations of learning algorithms. His research expertise spans: Machine Learning Statistical Learning Theory Harmonic Analysis Professor Vigogna's publication record demonstrates deep theoretical work connecting advanced mathematics to machine learning. His research investigates the spectral properties, geometric structure, and convergence behavior of neural networks using functional analysis and harmonic analysis techniques. Notable publications include his 2022 ICML paper on multiclass learning with exponential convergence rates and numerous works exploring the mathematical properties of deep learning systems through reproducing kernel spaces. He teaches Statistica for the Master's program in Environmental Biology and Statistical Learning for the Master's program in Pure and Applied Mathematics, reflecting his dual expertise in mathematical theory and practical data science applications. Professor Vigogna maintains active collaborations with leading researchers including Lorenzo Rosasco and Ernesto De Vito, advancing our fundamental understanding of learning algorithms through rigorous mathematical analysis. His work represents an essential bridge between pure mathematics and the theoretical foundations of modern artificial intelligence.

• Machine Learning
• Statistical Learning Theory
• Harmonic Analysis