| One practical algorithm for both stochastic and adversarial bandits Y Seldin, A Slivkins Proceedings of the 31st International Conference on Machine Learning (ICML …, 2014 | 205 | 2014 |
| Enhanced electronic program guides M Goldenberg, Y Seldin, A Sterkin US Patent 8,181,201, 2012 | 189 | 2012 |
| Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits J Zimmert, Y Seldin Journal of Machine Learning Research 22 (28), 1-49, 2021 | 176 | 2021 |
| PAC-Bayesian inequalities for martingales Y Seldin, F Laviolette, N Cesa-Bianchi, J Shawe-Taylor, P Auer IEEE Transactions on Information Theory 58 (12), 7086-7093, 2012 | 153 | 2012 |
| An Optimal Algorithm for Stochastic and Adversarial Bandits J Zimmert, Y Seldin International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 | 145 | 2019 |
| A Strongly Quasiconvex PAC-Bayesian Bound N Thiemann, C Igel, O Wingenberger, Y Seldin Algorithmic Learning Theory (ALT), 2017 | 123 | 2017 |
| An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits Y Seldin, G Lugosi Conference on Learning Theory (COLT), 2017 | 119 | 2017 |
| PAC-Bayes-Empirical-Bernstein Inequality IO Tolstikhin, Y Seldin Advances in Neural Information Processing Systems, 109-117, 2013 | 119 | 2013 |
| Online learning in Markov decision processes with adversarially chosen transition probability distributions Y Abbasi, P Bartlett, V Kanade, Y Seldin, C Szepesvári Advances in Neural Information Processing Systems, 2508-2516, 2013 | 113* | 2013 |
| PAC-Bayesian Analysis of Co-clustering and Beyond. Y Seldin, N Tishby Journal of Machine Learning Research 11 (12), 2010 | 109 | 2010 |
| Prediction with limited advice and multiarmed bandits with paid observations Y Seldin, P Bartlett, K Crammer, Y Abbasi-Yadkori Proceedings of the 31st International Conference on Machine Learning (ICML …, 2014 | 93 | 2014 |
| Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments Y Seldin, C Szepesvári, P Auer, Y Abbasi-Yadkori | 87 | 2013 |
| An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays J Zimmert, Y Seldin International Conference on Artificial Intelligence and Statistics (AISTATS), 2020 | 74 | 2020 |
| Nonstochastic Multiarmed Bandits with Unrestricted Delays TS Thune, N Cesa-Bianchi, Y Seldin Advances in Neural Information Processing Systems (NeurIPS), 2019 | 73 | 2019 |
| PAC-Bayesian analysis of contextual bandits Y Seldin, P Auer, JS Shawe-Taylor, R Ortner, F Laviolette Advances in neural information processing systems, 1683-1691, 2011 | 62 | 2011 |
| Second order PAC-Bayesian bounds for the weighted majority vote AR Masegosa, SS Lorenzen, C Igel, Y Seldin Advances in Neural Information Processing Systems (NeurIPS), 2020 | 61 | 2020 |
| Multi-dueling bandits and their application to online ranker evaluation B Brost, Y Seldin, IJ Cox, C Lioma Proceedings of the 25th ACM International on Conference on Information and …, 2016 | 49 | 2016 |
| Unsupervised clustering of images using their joint segmentation Y Seldin, S Starik, M Werman 3rd International Workshop on Statistical and Computational Theories of …, 2003 | 45 | 2003 |
| Method for content presentation Y Seldin, A Sterkin US Patent 8,220,023, 2012 | 39 | 2012 |
| An algorithm for stochastic and adversarial bandits with switching costs C Rouyer, Y Seldin, N Cesa-Bianchi International Conference on Machine Learning, 9127-9135, 2021 | 34 | 2021 |
Nicolò Cesa-BianchiProfessor of Computer Science, Università degli Studi di Milano and Politecnico di MilanoVerified email at unimi.it
