Affiliated PhD Fellow - UiT The Arctic University of Norway, Department of Mathematics and Statistics
Academic interests
Roberto’s research centers on foundational machine learning for time series and graph-structured data. His work emphasizes uncertainty quantification in high-dimensional multivariate time series, with a particular focus on methodological validity and computational scalability. To address these challenges, he integrates statistical frameworks, such as conformal prediction, with modern deep learning approaches, including diffusion models, normalizing flows, and randomized architectures like reservoir computing.
Background
Prior to his Ph.D., Roberto earned a dual Master’s degree from Politecnico di Milano (Italy) in High Performance Computing Engineering and from Università della Svizzera Italiana (Switzerland) in Computational Science. He previously completed a Bachelor’s degree in Computer Science Engineering at Politecnico di Milano, during which he also gained industry experience at Deloitte.
PhD project
"Machine Learning for Graphs and Time Series Data"
Supervisors
- Filippo Maria Bianchi, UiT - the Arctic University of Norway, Department of Mathematics
- Carlo Abate, UiT - the Arctic University of Norway, Department of Mathematics
- Andrea Cini, Swiss National Science Foundation postdoc fellow at the University of Oxford