Yevgeny Seldin
Professor
Machine Learning
Universitetsparken 1
2100 København Ø
- 2020
- Published
Tsallis-INF for decoupled exploration and exploitation in multi-armed bandits
Rouyer, C. & Seldin, Yevgeny, 2020, Proceedings of Thirty Third Conference on Learning Theory(COLT). PMLR, p. 3227-3249 (Proceedings of Machine Learning Research, Vol. 125).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- 2019
- Published
An Optimal Algorithm for Stochastic and Adversarial Bandits
Zimmert, J. U. & Seldin, Yevgeny, 2019, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS). Chaudhuri, K. & Sugiyama, M. (eds.). PMLR, p. 467-475 (Proceedings of Machine Learning Research, Vol. 89).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
Nonstochastic multiarmed bandits with unrestricted delays
Thune, T. S., Cesa-Bianchi, N. & Seldin, Yevgeny, 2019, Advances in Neural Information Processing Systems 32 (NeurIPS). NIPS Proceedings, 10 p.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
On PAC-Bayesian bounds for random forests
Lorenzen, S. S., Igel, Christian & Seldin, Yevgeny, 2019, In: Machine Learning. 108, 8-9, p. 1503-1522Research output: Contribution to journal › Journal article › Research › peer-review
- 2018
- Published
Adaptation to Easy Data in Prediction with Limited Advice
Thune, T. S. & Seldin, Yevgeny, 2018, Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada. NIPS Proceedings, 10. (Advances in Neural Information Processing Systems, Vol. 31).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
Factored Bandits
Zimmert, J. U. & Seldin, Yevgeny, 2018, Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada.. NIPS Proceedings, 10 p. (Advances in Neural Information Processing Systems, Vol. 31).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- 2017
- Published
A strongly quasiconvex PAC-Bayesian bound
Thiemann, N., Igel, Christian, Wintenberger, O. & Seldin, Yevgeny, 2017, Proceedings of International Conference on Algorithmic Learning Theory, 15-17 October 2017, Kyoto University, Kyoto, Japan . Hanneke, S. & Reyzin, L. (eds.). Proceedings of Machine Learning Research, p. 466-492 (Proceedings of Machine Learning Research, Vol. 76).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
An improved parametrization and analysis of the EXP3++ algorithm for stochastic and adversarial bandits
Seldin, Yevgeny & Lugosi, G., 2017, Proceedings of Conference on Learning Theory, 7-10 July 2017, Amsterdam, Netherlands. Kale, S. & Shamir, O. (eds.). Proceedings of Machine Learning Research, p. 1743-1759 (Proceedings of Machine Learning Research, Vol. 65).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- 2016
- Published
An improved multileaving algorithm for online ranker evaluation
Brost, B., Cox, Ingemar Johansson, Seldin, Yevgeny & Lioma, Christina, 2016, Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval: SIGIR '16. Association for Computing Machinery, p. 745-748 4 p.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
Multi-dueling bandits and their application to online ranker evaluation
Brost, B., Seldin, Yevgeny, Cox, Ingemar Johansson & Lioma, Christina, 2016, Proceedings of the 25th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, p. 2161-2166 6 p. (ACM International Conference on Information and Knowledge Management).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
ID: 120818606
Most downloads
-
72
downloads
Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Published -
30
downloads
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Published -
28
downloads
Tsallis-INF: An optimal algorithm for stochastic and adversarial bandits
Research output: Contribution to journal › Journal article › Research › peer-review
Published