About Me
Gianmarco Genalti is a Ph.D. student at the Artificial Intelligence and Robotic Laboratory (AIRLab) at the Department of Electronics, Information, and Bioengineering of Politecnico di Milano. He graduated in Mathematical Engineering M.Sc. at Politecnico di Milano in 2021, in the Statistical Learning track. During his studies, he worked as Data Scientist and Applied Scientist, while performing academic research on multiple topics. Currently, he's also working on industrial research projects as a research collaborator of the AI research center of Politecnico di Milano.
Education
Ph.D. Student in Data Analytics and Decision Sciences - Politecnico di Milano (Nov 2022 - now)
Research topics: Multi-Armed Bandits, Online Learning, Reinforcement Learning, Industrial Applications of AI
M.Sc. in Mathematical Engineering - Politecnico di Milano (Sep 2019 - Dec 2021)
Main focus: Statistics and Machine Learning
Relevant coursework: Statistics, Machine Learning, Online Learning, Mathematical Analysis, Discrete Mathematics, Algorithmic Game Theory, Operational Research, Parallel Computing.
B.Sc. in Mathematical Engineering - Politecnico di Milano (Sep 2016 - Mar 2020)
Relevant coursework: Calculus, Statistics, Probability, Numerical Analysis, Linear Algebra and Geometry, Physics, Applied Physics.
Publications & Research Activity
[COLT24] Gianmarco Genalti, Lupo Marsigli, Nicola Gatti and Alberto Maria Metelli. (ε,u)-Adaptive Regret Minimization in Heavy-Tailed Bandits. To appear in Conference on Learning Theory, 2024.
[Link - To Appear]
[Paper - To Appear]
[Poster - To Appear]
[Slides - To Appear]
[ICML24a] Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli. Graph-Triggered Rising Bandits. To appear in International Conference on Machine Learning, 2024.
[Link - To Appear]
[Paper - To Appear]
[Poster - To Appear]
[ICML24b] Jacopo Germano, Francesco E. Stradi, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti. Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints. To appear in International Conference on Machine Learning, 2024.
[Link - To Appear]
[Paper - To Appear]
[Poster - To Appear]
[AISTATS24] Francesco Bacchiocchi*, Gianmarco Genalti*, Davide Maran*, Marco Mussi*, Marcello Restelli, Nicola Gatti and Alberto Maria Metelli. Autoregressive Bandits. International Conference on Artificial Intelligence and Statistics, 2024.
[Link]
[Paper]
[Poster]
[Slides]
[IJCAI24] Gianmarco Genalti, Gabriele Corbo, Tommaso Bianchi, Marco Missaglia, Luca Negri, Andrea Sala, Luca Magri, Giacomo Boracchi, Giovanni Miragliotta, Nicola Gatti. Enhancing Manufacturing with AI-powered Process Design. To appear in The 33rd International Joint Conference on Artificial Intelligence, 2024.
[Link - To Appear]
[Paper]
[Video Presentation]
[AAAI23] Marco Mussi*, Gianmarco Genalti*, Alessandro Nuara, Francesco Trovò, Nicola Gatti and Marcello Restelli. Dynamic Pricing with Volume Discounts in Online Settings. Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
[Link]
[Paper]
[Poster]
[Slides]
[Award]
[KDD22] Marco Mussi, Gianmarco Genalti, Francesco Trovò, Alessandro Nuara, Nicola Gatti and Marcello Restelli. Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022. (Oral Presentation - 54/753 - top 7%)
[Link]
[Paper]
[Poster]
[Slides]
[BMJ21] Marta Spreafico, Francesca Ieva, Francesca Arlati, Federico Capello, Federico Fatone, Filippo Fedeli, Gianmarco Genalti, Jakob Anninga, Hans Gelderblom, Marta Fiocco. Novel longitudinal Multiple Overall Toxicity (MOTox) score to quantify adverse events experienced by patients during chemotherapy treatment: a retrospective analysis of the MRC BO06 trial in osteosarcoma. BMJ open (Q1 Scimago), Dec. 2021.
[Link]
[Paper]
[Technical Note 2025] Gianmarco Genalti and Alberto Maria Metelli. A Regret Lower Bound for u-Adaptive Heavy-Tailed Bandits
[Note]
Reviewer for International Conferences
NeurIPS 2023 (1) - ICLR 2024 (2) - ICML 2024 (6).
Academic Activites
Teaching Assistant, Online Learning and Applications - Politecnico di Milano (Feb 2024 - July 2024)
Teaching Assistant, Statistical Modelling and Stochastic Processes - Politecnico di Milano (Sep 2023 - Feb 2024)
Supervised Master Theses
Marco Lucchini. Designing a Reinforcement Learning-Based System for Optimal Odds Selection in Sports Betting. 2023.
Gabriele Corbo. Planning in Manufacturing with Data-driven Heuristics. 2023.
Marco Bonalumi. An Online Learning Algorithm for Real-Time Bidding. 2023.
Lupo Marsigli. Towards fully-adaptive regret minimization in heavy-tailed bandits. 2023.
Vittorio Arianna. Multi-armed bandits for joint pricing and advertising. 2023.
Francesco Fulco Gonzales. Stochastic linear bandits with global-local structure. 2023.
Davide Cairoli. Forecasting gas demand and optimizing set-point pressure for efficient gas distribution networks. 2023.
Industrial Research Projects
Process Planning in Metal Manifacturing (Agrati - PoliMi AIRIC, Jan 2022 - now)
Conceptualization of the planning problem underlying bolt manufacturing. Development of an optimization strategy to compute the production cycle starting from the technical drawing of a new component. Submission of a demo paper to IJCAI 2024 (see the work here).
Startup Investment Forecasting and Intelligence (Lutech - PoliMi AIRIC, Jan 2024 - now)
Analysis of large unstructured datasets for startup value prediction. Development of data-driven investment strategies.
Reinforcement Learning for Odds Optimization in Sports Betting (Snaitech - PoliMi AIRIC, Mar 2022 - now)
Development of a model-based reinforcement learning algorithm to propose odds in sports betting.
Forecasting Gas Demand and Distribution Network Optimization (Terranova Software - PoliMi AIRIC, Jan 2022 - May 2023)
Development of a forecasting model for real-time gas demand in different Italian cities. Development of a strategy for distribution network optimization under physical and economical constraints.
Working Experience
AI Research Scientist - AIRIC, Politecnico di Milano (Milan, Jan 2021 - now)
Member of the AI industrial research group (AIRIC), working in multiple joint projects between industry and academy.
Applied Scientist - ML cube (Milan, Feb 2021 - Dec 2021)
Member of the development team of an innovative product for the dynamic pricing of products in e-commerce.
Data Scientist - Philip Morris International (Lausanne, Aug 2020 - Jan 2021)
Member of the Business Intelligence and Data Science team of the PMI Duty Free office in Lausanne (CH).