Embedded Files
About me
About me
Postdoctoral Scholar
Istituto Italiano di Tecnologia (IIT) · Genova, Italy
My research focuses on the mathematical foundations of deep learning, examining how network architecture, compositional structure, and learned representations shape generalization and sample complexity.
At IIT, I work with Lorenzo Rosasco. My doctoral research was conducted at City University of Hong Kong (PhD in Mathematics, 2023), under the supervision of Han Feng and Ding-Xuan Zhou. In October 2025, I visited Tomaso Poggio’s group at MIT.
📣 News
📣 News
🌟 Sep. 2026 · Our paper Learning Sparse Compositional Functions with Norm-Constrained Neural Networks has been accepted at NeurIPS 2026.
April 2026 · New preprint on sparsity-aware neural networks for nonlinear functionals, with approximation guarantees that mitigate dimensional dependence.
March 2026 · Spherical Analysis of Learning Nonlinear Functionals was published in Constructive Approximation.
Research interests
Research interests
My work brings together statistical learning theory, approximation theory, harmonic analysis, and kernel methods.
Learning theory: learning rates and generalization for structured neural networks.
Representation learning: compositionality, kernel methods, and low-dimensional structure.
Operator learning: neural approximation with infinite-dimensional inputs.
Page updated
Google Sites
Report abuse