Fetching the paper…
Reading the bibliography…
We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the sample size n.
Probability inequalities for sums of bounded random variables
W. Hoeffding · 1963
Earlier work this paper cites.
Relating data compression and learnability
N. Littlestone and M. K. Warmuth · 1986
Earlier work this paper cites.
The Nature of Statistical Learning Theory
V. Vapnik · 1995
Earlier work this paper cites.
The Importance of Convexity in Learning with Squared Loss
W. S. Lee, P. L. Bartlett, R. C. Williamson · 1998
Cited alongside, same era.
Concentration
C. McDiarmid · 1998
Cited alongside, same era.
Neural Network Learning: Theoretical Foundations
M. Anthony and P. Bartlett · 1999
Cited alongside, same era.
Exploration-exploitation trade-off using variance estimates in multi-armed bandits
J. Y. Audibert, R. Munos, C. Szepesvári
Cited in the paper.
Covering numbers for support vector machines
Y. G. Guo, P. L. Bartlett, J. Shawe-Taylor, R. C. Williamson · 1999
Later among the works it cites.
Concentration inequalities for functions of independent variables
A. Maurer · 2006
Later among the works it cites.
Empirical Bernstein Stopping
V. Mnih, C. Szepesvári, J. Y. Audibert · 2008
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…