Yevgeny Seldin
Professor
Machine Learning
Universitetsparken 1
2100 København Ø
Prediction with limited advice and multiarmed bandits with paid observations
Seldin, Yevgeny, Bartlett, P. L., Crammer, K. & Abbasi-Yadkori, Y., 2014, JMLR Workshop and Conference Proceedings, 32 (ICML).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
Masegosa, A. R., Lorenzen, S. S., Igel, Christian & Seldin, Yevgeny, 2020, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. NeurIPS Proceedings, (Advances in Neural Information Processing Systems, Vol. 33).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- Published
Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables
Wu, Yi-Shan & Seldin, Yevgeny, 2022, Advances in Neural Information Processing Systems 35 (NeurIPS 2022). NeurIPS Proceedings, p. 11369-11381Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
- 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
- Published
Tsallis-INF: An optimal algorithm for stochastic and adversarial bandits
Zimmert, J. U. & Seldin, Yevgeny, 2021, In: Journal of Machine Learning Research. 22, 49 p., 28.Research output: Contribution to journal › Journal article › Research › peer-review
- Published
Unsupervised segmentation and classification of mixtures of Markovian sources
Seldin, Yevgeny, Starik, S. & Werman, M., 2003.Research output: Contribution to conference › Paper › Research › peer-review
- Published
Unsupervised sequence segmentation by a mixture of variable memory length Markov sources
Seldin, Yevgeny, Bejerano, G. & Tishby, N., 2001, Proceedings of the 18th International Conference on Machine Learning (ICML).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
ID: 120818606
Most downloads
-
74
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 -
31
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 -
29
downloads
Tsallis-INF: An optimal algorithm for stochastic and adversarial bandits
Research output: Contribution to journal › Journal article › Research › peer-review
Published