Back to list

Saverio Salzo


Research Line

Computational Statistics and Machine Learning


IIT Central Research Labs Genova

+39 010 2897 413

Social profiles

researchgate googlescholar linkedin


Saverio Salzo received an MSc degree in Mathematics from University of Bari in 2001 (summa cum laude) and a PhD in Computer Science from University of Genoa in 2012. His main research interests are in convex optimization, hyperparameter optimization, stochastic algorithms, regularization methods, and machine learning. Since 2018 he has been a researcher at Italian Institute of Tecnology (IIT) within the group Computational Statistics and Machine Learning led by Massimiliano Pontil. Previously, he was a post-doctoral fellow at IIT in the Laboratory for Computational and Statistical Learning led by Lorenzo Rosasco (2016–2018) and at University of Genoa (2012–2016).


Convex optimization stochastic algorithms hyperparameter optimization machine learning

Selected Publications

  • S Villa, S Salzo, L Baldassarre, A Verri, Accelerated and Inexact Forward-Backward Algorithms, SIOPT, 2013
  • S Salzo, The variable metric forward-backward splitting algorithm under mild differentiability assumptions, SIOPT 2017
  • S Salzo, JAK Suykens, L Rosasco, Solving lp-norm regularization with tensor kernels, AISTATS 2018
  • L. Franceschi, P. Frasconi, S. Salzo, R. Grazzi, and M. Pontil, Bilevel programming for hyperparameter optimization and meta-learning, ICML 2018
  • PL Combettes, S Salzo, S Villa, Consistent learning by composite proximal thresholding, Math. Program., 2019
  • G Luise, S Salzo, M Pontil, C Ciliberto, Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm, NeurIPS 2019


IIT's website uses the following types of cookies: browsing/session, analytics, functional and third party cookies. Users can choose whether or not to accept the use of cookies and access the website. By clicking on "Further Information", the full information notice on the types of cookies will be displayed and you will be able to choose whether or not to accept them whilst browsing on the website
Further Information
Accept and close