Sciweavers

JMLR
2012
11 years 7 months ago
PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The fi...
Yevgeny Seldin, Nicolò Cesa-Bianchi, Peter ...