Publications

International Conferences

[1] Davide Maran, Alberto Maria Metelli, Matteo Papini and Marcello Restelli. Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024.
[Link - To Appear] [Paper]

[2] Davide Maran, Francesco Bacchiocchi*, Francesco Emanuele Stradi*, Matteo Castiglioni, Nicola Gatti and Marcello Restelli. Bandits with Ranking Feedback. Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024.
[Link - To Appear] [Paper]

[3] Davide Maran, Alberto Maria Metelli, Matteo Papini and Marcello Restelli. Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. Proceedings of the 37th Annual Conference on Learning Theory (COLT), 2024.
[Link] [Paper]

[4] Davide Maran, Alberto Maria Metelli, Matteo Papini and Marcello Restelli. No-Regret Reinforcement Learning in Smooth MDPs. Proceedings of the 41th International Conference on Machine Learning (ICML), 2024.
[Link] [Paper]

[5] Francesco Bacchiocchi*, Gianmarco Genalti*, Davide Maran*, Marco Mussi*, Marcello Restelli, Nicola Gatti and Alberto Maria Metelli. Autoregressive Bandits. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
[Link] [Paper]

[6] Davide Maran*, Pierriccardo Olivieri*, Francesco Emanuele Stradi*, Giuseppe Urso, Nicola Gatti and Marcello Restelli. Online Markov Decision Processes Configuration with Continuous Decision Space. Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024.
[Link] [Paper]

[7] Davide Maran, Alberto Maria Metelli and Marcello Restelli. Tight performance guarantees of imitator policies with continuous actions. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
[Link] [Paper]

[8] Pierre Liotet*, Davide Maran*, Lorenzo Bisi and Marcello Restelli. Delayed reinforcement learning by imitation. Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
[Official Site] [Link] [Paper]

Journals

[9] Matteo Gregoratti*, Davide Maran*. Least singular value and condition number of a square random matrix with iid rows. Statistics and Probability Letters. 2021.
[Link] [Paper]

Education

Visiting Student - University of Alberta (Sept 2024 - Dec 2024)
Host: Prof. Csaba Szepesvari

Ph.D. in Information Technology - Politecnico di Milano (Nov 2022 - now)
Ph.D. in Machine Learning. Research topic: Representation Learning for RL.
Supervisor: Prof. Marcello Restelli
Relevant coursework: Algorithmic Game Theory, Stochastic Dynamical Programming, Mathematical and numerical foundations of scientific machine learning.

M.Sc. in Mathematical Engineering - Politecnico di Milano (Sep 2019 - Dec 2021)
Final grade: 110/110 cum laude
Main focus: Statistics and Machine Learning
Relevant coursework: Machine Learning, Real and Functional Analysis, Applied Statistics, Artificial Neural Networks and Deep Learning

B.Sc. in Mathematical Engineering - Politecnico di Milano (Sep 2016 - Sep 2019)
Final grade: 103/110
Relevant coursework: Linear Algebra and Geometry, Probability, Numerical Mathematics

High School Diploma - Liceo Leonardo da Vinci, Gallarate (Sep 2011 - Jul 2016)
Main Focus: Mathematics, Physics

Experience

Visiting Student - University of Alberta (Sept 2024 - Dec 2024)
Host: Prof. Csaba Szepesvari

Research Assistant - Politecnico di Milano (Jan 2022 - Oct 2022)
Supervisor: Prof. Marcello Restelli

Academic Activities

Positions Held

Secretary of the Association of Mathematical Engineers
I was appointed secretary of the Association of Mathematical Engineers in the 2020 board. In addition to drawing up the minutes of the meetings, I was involved in organize various seminars, meetings with companies and team building events aimed at members.

Partecipation to International Events

International Conference on Machine Learning - ICML2024.
Vienna, Austria. July 2024.

Conference on Learning Theory - COLT2024.
Edmonton, Alberta, Canada. June 2024.

AAAI Conference on Artificial Intelligence - AAAI2024.
Vancouver, British Columbia, Canada. February 2024.

European Workshop on Reinforcement Learning - EWRL 2023
Brussels, Belgium. September 2023.

AAAI Conference on Artificial Intelligence - AAAI2023.
Washington DC, USA. February 2023.

European Workshop on Reinforcement Learning - EWRL 2022
Milan, Italy. September 2022.

International Conference on Machine Learning - ICML 2022
Baltimore, Mariland, USA. July 2022.

Master's Students Supervision

Giuseppe Urso - "Online Markov Decision Processes Configuration with Continuous De- cision Space". Co-supervision. Supervisor: Prof. Marcello Restelli, Msc. Marco Mussi (M.Sc. in Computer Science and Engineering, Jul 2023)

Oscar Francesco Pindaro - "Controlling Lithium-Ion Batteries Through Reinforcement Learning". Co-supervision. Supervisor: Prof. Marcello Restelli, Msc. Marco Mussi (M.Sc. in Computer Science and Engineering, Apr 2022)

Review

Reviewer for Journals:
Journal of Machine Learning Research (JMLR)
Reviewer for International Conferences and Workshops:
Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
European Workshop on Reinforcement Learning (EWRL)

Contacts

Email
davide DOT maran AT polimi DOT it

Office

Office 21, First Floor of Building 21
Dipartimento di Elettronica, Informazione e Bioingegneria
Politecnico di Milano
Via Ponzio 34/5, Milan, 20133, Italy