Access the full text.
Sign up today, get DeepDyve free for 14 days.
D Haussler (1992)
Decision theoretic generalizations of the PAC model for neural net and other learning applicationsInf. Comput., 100
D Pollard (1984)
10.1007/978-1-4612-5254-2
S Boucheron, O Bousquet, G Lugosi (2005)
Theory of classification: a survey of some recent advancesESAIM: Probab. Statist., 9
HIII Daumé (2006)
10.1613/jair.1872J. Artif. Intell. Res., 26
D Jaeschke (1979)
The asymptotic distribution of the supremum of the standardized empirical distribution function on subintervalsAnn. Stat., 7
V Koltchinskii, D Panchenko (2002)
Empirical margin distributions and bounding the generalization error of combined classifiersAnn. Statist., 30
SA Jaeger (2005)
Generalization bounds and complexities based on sparsity and clustering for convex combinations of functions from random classesJ. Mach. Learn. Res., 6
P Massart (2006)
10.1214/009053606000000786Ann. Stat., 34
PL Bartlett (2002)
10.1023/A:1013999503812Mach. Learn., 48
N Sauer (1972)
10.1016/0097-3165(72)90019-2J Combinat Theory, Ser A, 13
B Bercu, E Gassiat, E Rio (2002)
Concentration inequalities, large and moderate deviations for self-normalized empirical processesAnn. Probab., 30
VN Vapnik (2006)
10.1007/0-387-34239-7
M Anthony, J Shawe-Taylor (1993)
A result of Vapnik with applicationsDiscret. Appl. Math., 47
VN Vapnik, A Chervonenkis (1971)
On the uniform convergence of relative frequencies of events to their probabilitiesTheory Probab. Appl., 16
VN Vapnik (1998)
Statistical Learning Theory. Wiley
D Jaeschke (1979)
10.1214/aos/1176344558Ann. Stat., 7
M Talagrand (1994)
10.1214/aop/1176988847Ann. Probab., 22
K Azuma (1967)
Weighted sums of certain dependent random variablesTohoku Math. J., 19
N Sauer (1972)
On the density of families of setsJ Combinat Theory, Ser A, 13
VN Vapnik (2006)
Estimation of Dependences Based on Empirical Data, 2nd edn
HIII Daumé, D Marcu (2006)
Domain adaptation for statistical classifiersJ. Artif. Intell. Res., 26
RM Dudley (1987)
10.1214/aop/1176991978Ann. Probab., 14
W Hoeffding (1963)
Probability inequalities for sums of bounded random variablesJ. Am. Stat. Assoc., 58
B Bercu (2002)
10.1214/aop/1039548367Ann. Probab., 30
D Pollard (1989)
10.1214/ss/1177012394Stat. Sci., 4
C Cortes, M Mohri (2013)
Domain adaptation and sample bias correction theory and algorithm for regressionTheor. Comput. Sci., 519
D Haussler (1992)
10.1016/0890-5401(92)90010-DInf. Comput., 100
S Boucheron (2005)
10.1051/ps:2005018ESAIM: Probab. Statist., 9
RM Dudley (1987)
Universal Donsker classes and metric entropyAnn. Probab., 14
V Koltchinskii (2002)
10.1214/aos/1015362183Ann. Statist., 30
D Pollard (1984)
Convergence of Stochastic Processess
PL Bartlett, S Boucheron, G Lugosi (2002)
Model selection and error estimationMach. Learn., 48
D Pollard (1989)
Asymptotics via empirical processesStat. Sci., 4
VN Vapnik (1971)
10.1137/1116025Theory Probab. Appl., 16
M Anthony (1993)
10.1016/0166-218X(93)90126-9Discret. Appl. Math., 47
H Shimodaira (2000)
10.1016/S0378-3758(00)00115-4J. Stat. Plan. Infer., 90
VH Peña, TL Lai, Q-M Shao (2008)
Self-Normalized Processes
RM Dudley (1984)
A course on empirical processesLect. Notes Math., 1097
K Azuma (1967)
10.2748/tmj/1178243286Tohoku Math. J., 19
R Meir, T Zhang (2003)
Generalization Error Bounds for Bayesian Mixture AlgorithmsJ. Mach. Learn. Res., 4
I Steinwart (2007)
10.1214/009053606000001226Ann. Stat., 35
I Steinwart, C Scovel (2007)
Fast rates for support vector machines using gaussian kernelsAnn. Stat., 35
W Hoeffding (1963)
10.1080/01621459.1963.10500830J. Am. Stat. Assoc., 58
M Talagrand (1994)
Sharper bounds for gaussian and empirical processesAnn. Probab., 22
P Massart, É Nédélec (2006)
Risk bounds for statistical learningAnn. Stat., 34
H Shimodaira (2000)
Improving predictive inference under covariate shift by weighting the log-likelihood functionJ. Stat. Plan. Infer., 90
We present an extensive analysis of relative deviation bounds, including detailed proofs of two-sided inequalities and their implications. We also give detailed proofs of two-sided generalization bounds that hold in the general case of unbounded loss functions, under the assumption that a moment of the loss is bounded. We then illustrate how to apply these results in a sample application: the analysis of importance weighting.
Annals of Mathematics and Artificial Intelligence – Springer Journals
Published: Jan 8, 2019
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.