An inequality for uniform deviations of sample averages from their means

@inproceedings{Bartlett2004AnIF,
  title={An inequality for uniform deviations of sample averages from their means},
  author={Peter Bartlett},
  year={2004}
}
We derive a new inequality for uniform deviations of averages from their means. The inequality is a common generalization of previous results of Vapnik and Chervonenkis (1974) and Pollard (1986). Using the new inequality we obtain tight bounds for empirical loss minimization learning. 

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

A Result of Vapnik with Applications

Discrete Applied Mathematics • 1994
View 2 Excerpts

Sharper bounds for Gaussian and empirical processes

M. Talagrand
Annals of Probability • 1994
View 1 Excerpt

Rates of uniform almost sure convergence for empirical processes indexed by unbounded classes of functions

D. Pollard
1986
View 2 Excerpts

Probability inequalities for empirical processes and a law of the iterated logarithm

K. Alexander
Annals of Probability • 1984
View 1 Excerpt

Probability inequalities for sums of bounded random variables

W. Hoe ding
Jour - nal of the American Statistical Association • 1963
View 1 Excerpt

Similar Papers

Loading similar papers…