World's Best Scientists 2026 revealed!
Lorenzo Rosasco

Lorenzo Rosasco

D-Index & Metrics

Computer Science

D-Index
51
Citations
11307
World Ranking
5307
National Ranking
2441

Mathematics

D-Index
51
Citations
10577
World Ranking
1025
National Ranking
475

Overview

Lorenzo Rosasco is affiliated with MIT in the United States and has an extensive research portfolio spanning several areas within computer science and engineering. The primary fields of study in Rosasco's work are Computer Science and Engineering, reflecting a broad interdisciplinary approach to research challenges.

The scientist's subfields of study include:

  • Artificial Intelligence
  • Computational Mechanics
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Mathematical Physics

Rosasco's main research topics encompass:

  • Sparse and Compressive Sensing Techniques
  • Numerical methods in inverse problems
  • Domain Adaptation and Few-Shot Learning
  • Gaussian Processes and Bayesian Inference
  • Stochastic Gradient Optimization Techniques
  • Statistical Methods and Inference
  • Machine Learning and Data Classification

The scientist has collaborated frequently with several researchers in the field. Notable frequent co-authors include:

  • Ernesto De Vito
  • Silvia Villa
  • Marco Rando
  • Cesare Molinari
  • Lorenzo Natale

Regarding publication venues, Rosasco has contributed extensively to:

  • arXiv (Cornell University)
  • Zenodo (CERN European Organization for Nuclear Research)
  • eLife
  • CINECA IRIS Institutional Research Information System (University of Genoa)
  • Analysis and Applications

Recent papers authored or co-authored by Rosasco include:

  • Learning to predict target location with turbulent odor plumes, 2022, eLife
  • Learning new physics efficiently with nonparametric methods, 2022, The European Physical Journal C
  • In-domain versus out-of-domain transfer learning in plankton image classification, 2023, Scientific Reports
  • Kernel methods through the roof: handling billions of points efficiently, 2020, arXiv (Cornell University)
  • Understanding neural networks with reproducing kernel Banach spaces, 2022, Applied and Computational Harmonic Analysis

Best Publications

  • Holographic embeddings of knowledge graphs

    Maximilian Nickel;Lorenzo Rosasco;Tomaso Poggio

  • On Early Stopping in Gradient Descent Learning

    Yuan Yao;Lorenzo Rosasco;Lorenzo Rosasco;Andrea Caponnetto;Andrea Caponnetto

  • Kernels for Vector-Valued Functions: A Review

    Mauricio A. Álvarez;Lorenzo Rosasco;Neil D. Lawrence

  • Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review

    Tomaso A. Poggio;Hrushikesh Mhaskar;Hrushikesh Mhaskar;Lorenzo Rosasco;Brando Miranda

  • Are loss functions all the same

    Lorenzo Rosasco;Ernesto De Vito;Andrea Caponnetto;Michele Piana

  • Elastic-net regularization in learning theory

    Christine De Mol;Ernesto De Vito;Lorenzo Rosasco

  • On regularization algorithms in learning theory

    Frank Bauer;Sergei Pereverzev;Lorenzo Rosasco

  • Learning from Examples as an Inverse Problem

    Ernesto De Vito;Lorenzo Rosasco;Andrea Caponnetto;Umberto De Giovannini

  • Generalization Properties of Learning with Random Features

    Alessandro Rudi;Lorenzo Rosasco

  • Less is more: Nyström computational regularization

    Alessandro Rudi;Raffaello Camoriano;Lorenzo Rosasco

  • On Learning with Integral Operators

    Lorenzo Rosasco;Mikhail Belkin;Ernesto De Vito

  • Model Selection for Regularized Least-Squares Algorithm in Learning Theory

    E. De Vito;A. Caponnetto;L. Rosasco

  • Spectral algorithms for supervised learning

    L. Lo Gerfo;L. Rosasco;F. Odone;E. De Vito

  • Convergence of Stochastic Proximal Gradient Algorithm

    Lorenzo Rosasco;Lorenzo Rosasco;Silvia Villa;Bằng Công Vũ

  • Iterative Projection Methods for Structured Sparsity Regularization

    Lorenzo Rosasco;Alessandro Verri;Matteo Santoro;Sofia Mosci

  • Some Properties of Regularized Kernel Methods

    Ernesto De Vito;Lorenzo Rosasco;Andrea Caponnetto;Michele Piana

  • Solving structured sparsity regularization with proximal methods

    Sofia Mosci;Lorenzo Rosasco;Matteo Santoro;Alessandro Verri

  • FALKON: An Optimal Large Scale Kernel Method

    Alessandro Rudi;Luigi Carratino;Lorenzo Rosasco

  • Unsupervised learning of invariant representations

    Fabio Anselmi;Joel Z. Leibo;Lorenzo Rosasco;Jim Mutch

  • Unsupervised Learning of Invariant Representations in Hierarchical Architectures

    Fabio Anselmi;Joel Z. Leibo;Lorenzo Rosasco;Jim Mutch

  • Theory of Deep Learning III: explaining the non-overfitting puzzle

    Tomaso A. Poggio;Kenji Kawaguchi;Qianli Liao;Brando Miranda

  • Less is More: Nystr"om Computational Regularization

    Alessandro Rudi;Raffaello Camoriano;Lorenzo Rosasco

Frequent Co-Authors

Alessandro Verri
Alessandro Verri University of Genoa
Lorenzo Natale
Lorenzo Natale Italian Institute of Technology
Giorgio Metta
Giorgio Metta Italian Institute of Technology
Hrushikesh N. Mhaskar
Hrushikesh N. Mhaskar Claremont Graduate University
Joel Z. Leibo
Joel Z. Leibo DeepMind (United Kingdom)
Luigi Varesio
Luigi Varesio MRC Laboratory of Molecular Biology
Steve Smale
Steve Smale City University of Hong Kong
Ding-Xuan Zhou
Ding-Xuan Zhou University of Sydney
Alessandro Lazaric
Alessandro Lazaric Facebook (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

For students pursuing Mathematics in the USA, exploring related online degrees can expand career opportunities. Those interested in leadership or business roles might consider an easiest mba program to transition smoothly into management. These programs often offer flexibility and a practical curriculum suitable for math graduates.

If finding a balance between quality and accessibility is your priority, the easiest mba programs provide options that combine convenience with recognized credentials, helping graduates enhance their skill sets without compromising affordability or ease of admission.

For those aiming for advanced expertise in business administration, especially with a focus on research and leadership, looking into the cheapest online dba programs can be a smart move. These programs offer specialization while being budget-conscious, perfectly complementing a mathematical background.

Lastly, graduates eager to delve into finance-related domains might explore a cheap masters in finance. This degree leverages strong analytical skills from math studies and prepares students for broad careers in financial analysis, investment, or risk management.

Best Scientists Citing Lorenzo Rosasco

Trending Scientists

Recently Published Articles