Computational & statistical learning
Our aim is to advance the frontiers of learning theory and machine learning, while building algorithmic tools for the analysis of complex systems and high dimensional data.
Our aim is to advance the frontiers of learning theory and machine learning, while building algorithmic tools for the analysis of complex systems and high dimensional data.
Our scientific interests focus on harmonic analysis, inverse problems, PDE and machine learning.
We investigate different nuances of visual perception in artificial intelligence systems, where computer vision and machine learning are combined to obtain robust data-driven methods addressing a variety of problems.
We blend physics with machine learning and biological behavior to ask how organisms strive in a fluid environment dominated by uncertainty.
Ongoing grants
Ended grants
Research Fundings in the past 5yrs
Title | Year | Author | Venue |
---|---|---|---|
Fast approximation of orthogonal matrices and application to PCA | 2022 | C Rusu L Rosasco | Signal Processing |
Fast iterative regularization by reusing data | 2022 | C Vega C Molinari L Rosasco S Villa | ArXiv Preprint |
AI-based component management system for structured content creation, annotation, and publication. | 2022 | A Barla Annalisa M Cuneo SR Nunzi G Paniati A Vian | 5th International Conference on Intelligent Human Systems Integration (IHSI 2022): Integrating People and Intelligent Systems |
Physics Informed Shallow Machine Learning for Wind Speed Prediction | 2022 | D Lagomarsino-Oneto G Meanti N Pagliana A Verri A Mazzino L Rosasco A Seminara | ArXiv Preprint |
Optimal Transport losses and Sinkhorn algorithm with general convex regularization\n | 2022 | S Di Marino A Gerolin | ArXiv Preprint |
Semantic learning in a federated learning system | 2022 | VP Pastore Y Zhou NB Angel A Anwar S BIANCO | US Patent App. 17/022,140 |
Synthesis and Execution of Communicative Robotic Movements with Generative Adversarial Networks | 2022 | L Lastrico L Garello A Sciutti N Noceti F Mastrogiovanni F Rea | ArXiv Preprint |
Phenotype to genotype mapping using supervised and unsupervised learning | 2022 | VP Pastore A Oke S Capponi D Elnatan J Fung S Bianco | bioRxiv |
Grand-Canonical Optimal Transport | 2022 | S Di Marino M Lewin L Nenna | ArXiv Preprint |
Markerless vs. Marker-Based Gait Analysis: A Proof of Concept Study | 2022 | M Moro G Marchesi F Hesse F Odone M Casadio | ArXiv Preprint |