Research
Publications
2024
Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi. Repeated bilateral trade against a smoothed adversary. JMLR. To appear.
Nicolò Cesa-Bianchi, Tommaso Cesari, Riccardo Della Vecchia. Cooperative online learning with feedback graphs. TMLR, 2024.
Giulia Clerici, Pierre Laforgue, Nicolò Cesa-Bianchi. Linear bandits with memory. TMLR featured paper, 2024.
Daniela Angela Parletta, Andrea Paudice, Massimiliano Pontil, Saverio Salzo. High probability bounds for stochastic subgradient schemes with heavy tailed noise. SIAM Journal on Mathematics of Data Science. To appear.
Marco Bressan, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen. A theory of interpretable approximations. COLT 2024.
Marco Bressan, Emmanuel Esposito, Maximilian Thiessen. Efficient algorithms for learning monophonic halfspaces in graphs. COLT 2024.
Marco Bressan, Mauro Sozio. Fully-dynamic approximate decision trees with worst-case update time guarantees. ICML 2024.
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice. Margin-based active learning of multiclass classifiers. Journal of Machine Learning Research 25(127):1−45, 2024.
Marco Bressan, Leslie Ann Goldberg, Kitty Meeks, Marc Roth. Counting subgraphs in somewhere dense graphs. SIAM Journal on Computing. To appear.
Nataša Bolić, Tommaso Cesari, Roberto Colomboni. An online learning theory of brokerage. AAMAS 2024.
Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi. The role of transparency in repeated first-price auctions with unknown valuations. STOC 2024.
Khaled Eldowa, Andrea Paudice. General tail bounds for non-smooth stochastic mirror descent. AISTATS 2024.
Juliette Achddou, Nicolò Cesa-Bianchi, Pierre Laforgue. Multitask online learning: listen to the neighborhood buzz. AISTATS 2024.
Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, Nicolò Cesa-Bianchi. Best-of-both-worlds algorithms for linear contextual bandits. AISTATS 2024. Oral presentation.
Stephen Pasteris, Alberto Rumi, Fabio Vitale, Nicolò Cesa-Bianchi. Sum-max submodular bandits. AISTATS 2024.
Tamim El Ahmad, Luc Brogat-Motte, Pierre Laforgue, Florence d'Alché-Buc. Sketch in, sketch out: accelerating both learning and inference for structured prediction with kernels. AISTATS 2024.
2023
Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi, Andreas Krause. Multitask learning with no regret: from improved confidence bounds to active learning. NeurIPS 2023.
Khaled Eldowa, Emmanuel Esposito, Tommaso Cesari, Nicolò Cesa-Bianchi. On the minimax regret for online learning with feedback graphs. NeurIPS 2023. Spotlight presentation.
Tamim El Ahmad, Pierre Laforgue, Florence d'Alché-Buc. Fast kernel methods for generic Lipschitz losses via p-sparsified sketches. Transactions on Machine Learning Research, 2023.
Stephan Clémençon, Pierre Laforgue, Robin Vogel. Fighting selection bias in statistical learning: application to visual recognition from biased image databases. Journal of Nonparametric Statistics, 2023.
Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg, Nicolò Cesa-Bianchi. A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs. COLT 2023.
Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi. Repeated bilateral trade against a smoothed adversary. COLT 2023.
Emmanuel Esposito, Saeed Masoudian, Hao Qiu, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin. Delayed bandits: when do intermediate observations help? ICML 2023.
Dirk van der Hoeven, Ciara Pike-Burke, Hao Qiu, Nicolò Cesa-Bianchi. Trading-off payments and accuracy in online classification with paid stochastic experts. ICML 2023.
Giulia Clerici, Marco Tiraboschi. Citation is not collaboration: music-genre dependence of graph-related metrics in a music credits network. Sound and Music Computing Conference 2023.
Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Metelli, Marcello Restelli. Information-theoretic regret bounds for bandits with fixed expert advice. ITW 2023.
Marco Bressan, Matthias Lanzinger, Marc Roth. The complexity of pattern counting in directed graphs, parameterised by the outdegree. ACM STOC 2023.
Lukas Zierahn, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Gergely Neu. Nonstochastic contextual combinatorial bandits. AISTATS 2023.
Nicolò Cesa-Bianchi, Tommaso Cesari, Takayuki Osogami, Marco Scarsini, Segev Wasserkrug. Learning the Stackelberg equilibrium in a newsvendor game. AAMAS 2023.
Marco Bressan, Gabriel Damay, Mauro Sozio. Fully-dynamic decision trees. AAAI 2023.
Marco Bressan, Leslie Ann Goldberg, Kitty Meeks, Marc Roth. Counting subgraphs in somewhere dense graphs. ITCS 2023.
Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi. Bilateral trade: a regret minimization perspective. Mathematics of Operations Research, 2023.
Marco Bressan, Enoch Peserico, Luca Pretto. Sublinear algorithms for local graph-centrality estimation. SIAM Journal on Computing 52(4):968-1008, 2023.
2022
Stephan Clémençon, Pierre Laforgue. Statistical learning from biased training samples. Electron. J. Statist. 16(2):6086-6134, 2022.
Chloé Rouyer, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin. A near-optimal best-of-both-worlds algorithm for online learning with feedback graphs. NeurIPS 2022.
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice, Maximilian Thiessen. Active learning of classifiers with label and seed queries. NeurIPS 2022.
Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi. A regret-variance trade-off in online learning. NeurIPS 2022.
Emmanuel Esposito, Federico Fusco, Dirk van der Hoeven, Nicolò Cesa-Bianchi. Learning on the edge: online learning with stochastic feedback graphs. NeurIPS 2022.
Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Claudio Gentile, and Yishay Mansour. Nonstochastic bandits with composite anonymous feedback. Journal of Machine Learning Research, 23(227):1-24, 2022.
Dirk van der Hoeven and Nicolò Cesa-Bianchi. Nonstochastic bandits and experts with arm-dependent delays. AISTATS 2022.
Pierre Laforgue, Giulia Clerici, Nicolò Cesa-Bianchi, and Ran Gilad-Bachrach. A last switch dependent analysis of satiation and seasonality in bandits. AISTATS 2022.
Nicolò Cesa-Bianchi, Pierre Laforgue, Andrea Paudice, and Massimiliano Pontil. Multitask online mirror descent. Transactions on Machine Learning Research, 2022.
Dirk van der Hoeven, Hédi Hadiji, and Tim van Erven. Distributed online learning for joint regret with communication constraints. ALT 2022.