Empirical Bernstein stopping
暂无分享,去创建一个
Csaba Szepesvári | Volodymyr Mnih | Jean-Yves Audibert | Csaba Szepesvari | Volodymyr Mnih | Jean-Yves Audibert
[1] W. Hoeffding. Probability Inequalities for sums of Bounded Random Variables , 1963 .
[2] Andrew W. Moore,et al. Hoeffding Races: Accelerating Model Selection Search for Classification and Function Approximation , 1993, NIPS.
[3] Osamu Watanabe,et al. Scaling Up a Boosting-Based Learner via Adaptive Sampling , 2000, PAKDD.
[4] Richard M. Karp,et al. An Optimal Algorithm for Monte Carlo Estimation , 2000, SIAM J. Comput..
[5] Osamu Watanabe,et al. MadaBoost: A Modification of AdaBoost , 2000, COLT.
[6] Leslie Pack Kaelbling,et al. Sampling Methods for Action Selection in Influence Diagrams , 2000, AAAI/IAAI.
[7] Geoff Hulten,et al. A General Method for Scaling Up Machine Learning Algorithms and its Application to Clustering , 2001, ICML.
[8] Shie Mannor,et al. PAC Bounds for Multi-armed Bandit and Markov Decision Processes , 2002, COLT.
[9] Andrew W. Moore,et al. The Racing Algorithm: Model Selection for Lazy Learners , 1997, Artificial Intelligence Review.
[10] I. Pinelis. On inequalities for sums of bounded random variables , 2006, math/0603030.
[11] Csaba Szepesvári,et al. Tuning Bandit Algorithms in Stochastic Environments , 2007, ALT.
[12] Joseph K. Bradley,et al. FilterBoost: Regression and Classification on Large Datasets , 2007, NIPS.
[13] Csaba Szepesvári,et al. Variance estimates and exploration function in multi-armed bandit , 2008 .