From post

The Perceptron Algorithm Versus Winnow: Linear Versus Logarithmic Mistake Bounds when Few Input Variables are Relevant (Technical Note).

, , и . Artif. Intell., 97 (1-2): 325-343 (1997)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

 

Другие публикации лиц с тем же именем

UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem., и . Period. Math. Hung., 61 (1-2): 55-65 (2010)PAC Subset Selection in Stochastic Multi-armed Bandits., , , и . ICML, icml.cc / Omnipress, (2012)Noisy Search with Comparative Feedback, и . CoRR, (2012)Generic Object Recognition with Boosting., , , и . IEEE Trans. Pattern Anal. Mach. Intell., 28 (3): 416-431 (2006)Online Learning.. Encyclopedia of Machine Learning, Springer, (2010)Exploration and Exploitation in Online Learning.. ICAIS, том 6943 из Lecture Notes in Computer Science, стр. 2. Springer, (2011)PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits., , , , и . ICML On-line Trading of Exploration and Exploitation, том 26 из JMLR Proceedings, стр. 98-111. JMLR.org, (2012)Autonomous Exploration For Navigating In MDPs., и . COLT, том 23 из JMLR Proceedings, стр. 40.1-40.24. JMLR.org, (2012)Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring., , , и . ALT, том 4264 из Lecture Notes in Computer Science, стр. 229-243. Springer, (2006)Simulating Access to Hidden Information while Learning, и . Electron. Colloquium Comput. Complex., (2000)