Davide D'Ascenzo
Davide D'Ascenzo

Italian National PhD Student in AI

Università degli Studi di Milano
Politecnico di Torino

About Me

I am a PhD student in Artificial Intelligence at Università degli Studi di Milano and Politecnico di Torino. My research focuses on the theoretical foundations of deep learning, with a particular interest in graph neural networks, graph-structured data, and learning on complex networks. Recently, I have begun exploring single-cell omics, developing predictive models of cellular responses. I am passionate about bridging theoretical insights with practical applications in machine learning and network science.

Download CV
Interests
  • Theoretical Deep Learning
  • Geometric Deep Learning
  • Graph Neural Networks
Education

  • PhD Artificial Intelligence

    Università degli Studi di Milano Politecnico di Torino

  • M.Sc. Computer Science

    Università degli Studi di Milano

  • B.Sc. Computer Science

    Università degli Studi di Milano

Featured Publications
scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
Position: A Theory of Deep Learning Must Include Compositional Sparsity
Hierarchical cross-entropy loss improves atlas-scale single-cell annotation models
Recent Publications
Davide D'Ascenzo, Sebastiano Cultrera Di Montesano (2025). scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics.
Cite arXiv URL
David A. Danhofer, Davide D'Ascenzo, Rafael Dubach, Tomaso a Poggio (2025). Position: A Theory of Deep Learning Must Include Compositional Sparsity. Forty-second International Conference on Machine Learning Position Paper Track.
Cite URL
Sebastiano Cultrera Di Montesano, Davide D'Ascenzo, Srivatsan Raghavan, Ava P. Amini, Peter S. Winter, Lorin Crawford (2025). Hierarchical cross-entropy loss improves atlas-scale single-cell annotation models. bioRxiv.
Cite DOI URL
Paolo Boldi, Davide D'Ascenzo, Flavio Furia, Sebastiano Vigna (2024). Score and rank semi-monotonicity for closeness, betweenness, and distance--decay centralities. Social Network Analysis and Mining.
Cite DOI URL
Paolo Boldi, Davide D'Ascenzo, Flavio Furia, Sebastiano Vigna (2024). Score and Rank Semi-monotonicity for Closeness, Betweenness and Harmonic Centrality. Complex Networks & Their Applications XII.
Cite