[People] - Introduction

IIT People Search

Massimiliano Pontil

Senior Researcher Tenured - Principal Investigator
Computational Statistics and Machine Learning
Phone
Research center
About

Massimiliano Pontil is Senior Researcher at the Italian Institute of Technology (IIT), where he leads the Computational Statistics and Machine Learning group, and co-director of the ELLIS Unit Genoa, a joint effort of IIT and the University of Genoa. He is also part-time professor at University College London and member of the UCL Centre for Artificial Intelligence. He has made significant contributions to machine learning, particularly in the areas of kernel methods, multitask and transfer learning, sparsity regularization and statistical learning theory. Recent interests include meta-learning, algorithm fairness and hyperparameter optimization. He was awarded the Best Paper Runner Up Award from ICML 2013, an EPSRC Advanced Research Fellowship in 2006-2011, and the Edoardo R. Caianiello Award for the Best Italian PhD Thesis on Connectionism in 2002.  He has published about 130 papers at international journals and conferences. His research papers have been cited approximately 12,000 times and his h-index is 48 (source Scopus, March 2022). He is regularly on the programme committee of the main machine learning conferences (COLT, ICML and NeurIPS), has been on the editorial board of the Machine Learning Journal, Statistics and Computing, JMLR, and was on the Scientific Advisory Board of Max Planck Institute for Intelligent Systems during 2013-2020. He has held visiting positions at a number of universities and research institutes, including the Isaac Newton Institute for Mathematical Sciences in Cambridge, the Catholic University of Leuven, the City University of Hong Kong, the University Carlos III de Madrid and ENSAE Institute Polytechnique Paris.

Education

Title: Ph.D. in Physics
Institute: University of Genoa
Location: Genoa
Country: Italy
From: 1996 To: 1999

All Publications
2022
Akhavan A., Chzhen E., Pontil M., Tsybakov A. B.
A gradient estimator via L1-randomization for online zero-order optimization with two point feedback
Advances in Neural Information Processing Systems, vol. 35
Conference Paper Conference
2022
Tremmel C., Fernandez-Vargas J., Stamos D., Cinel C., Pontil M., Citi L., Poli R.
A meta-learning BCI for estimating decision confidence
Journal of Neural Engineering, vol. 19, (no. 4)
Article Journal
2022
Kostic V. R., Salzo S., Pontil M.
Batch Greenkhorn Algorithm for Entropic-Regularized Multi- marginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity
International Conference on Machine Learning ICML 2022, vol. 162, pp. 11529-11558
Article Conference
2022
Frecon J., Gasso G., Pontil M., Salzo S.
Bregman Neural Networks
Proceedings of the 39 th International Conference on Machine Learning
Conference Paper Conference
2022
Novelli P., Bonati L., Pontil M., Parrinello M.
Characterizing Metastable States with the Help of Machine Learning
Journal of Chemical Theory and Computation, vol. 18, (no. 9), pp. 5195-5202
Awards and Achievements
2022
Pontil M.
co-Director ELLIS Genoa Unit
2022
Pontil M.
Spoke Leader
2020
Pontil M.
Advisory Board, Max Planck Institute for Intelligent Systems, Germany
2020
Pontil M.
Elected ELLIS Fellow
2013
Pontil M.
Best Paper Runner Up
Editorships
2014-2016
Pontil M.
International Conference on Machine Learning (ICML)
2013-2023
Pontil M.
Journal of Machine Learning Research
2013-2015
Pontil M.
Neural Information Processing Systems
2009-2018
Pontil M.
Machine Learning Journal
2008-2011
Pontil M.
Annual Conference on Learning Theory (COLT)
Organized Events
2021
Chzhen E., Pontil M., Valera I.
Foundations of Algorithmic Fairness
2018
Pontil M.
American Association on Artificial Intelligence (AAAI) Area Chair
2017
Pontil M.
Workshop on Prioritising Online Content
2015
Pontil M.
Dagstuhl Workshop on "Machine Learning with Interdependent and Non-identically Distributed Data".
2012
Pontil M.
ICML Workshop entitled “Object, Functional and Structured Data: Towards Next Generation Kernel-Based Methods”

[People] - Disclaimer