\begin{thebibliography}{}

\bibitem[Akaike, 1970]{Aka:1969}
Akaike, H. (1970).
\newblock Statistical predictor identification.
\newblock {\em Ann. Inst. Statist. Math.}, 22:203--217.

\bibitem[Akaike, 1973]{Aka:1973}
Akaike, H. (1973).
\newblock Information theory and an extension of the maximum likelihood
  principle.
\newblock In {\em Second International Symposium on Information Theory
  (Tsahkadsor, 1971)}, pages 267--281. Akad\'emiai Kiad\'o, Budapest.

\bibitem[Allen, 1974]{All:1974}
Allen, D.~M. (1974).
\newblock The relationship between variable selection and data augmentation and
  a method for prediction.
\newblock {\em Technometrics}, 16:125--127.

\bibitem[Alpaydin, 1999]{Alp:1999}
Alpaydin, E. (1999).
\newblock Combined 5 x 2 cv {F} test for comparing supervised classification
  learning algorithms.
\newblock {\em Neur. Comp.}, 11(8):1885--1892.

\bibitem[Anderson et~al., 1972]{AnAB72}
Anderson, R.~L., Allen, D.~M., and B., C.~F. (1972).
\newblock Selectioon of predictor variables in linear multiple regression.
\newblock In bancroft, T.~A., editor, {\em In Statistical papers in Honor of
  George W. Snedecor}. Iowa: iowa State University Press.

\bibitem[Arlot, 2007]{Arlo07}
Arlot, S. (2007).
\newblock {\em Resampling and Model Selection}.
\newblock PhD thesis, University Paris-Sud 11.
\newblock oai:tel.archives-ouvertes.fr:tel-00198803\_v1.

\bibitem[Arlot, 2008a]{Arlo08c}
Arlot, S. (2008a).
\newblock Model selection by resampling penalization.
\newblock {\em Electronic Journal of Statistics}.
\newblock To appear. oai:hal.archives-ouvertes.fr:hal-00262478\_v1.

\bibitem[Arlot, 2008b]{Arlo08}
Arlot, S. (2008b).
\newblock Suboptimality of penalties proportional to the dimension for model
  selection in heteroscedastic regression.
\newblock arXiv:0812.3141.

\bibitem[Arlot, 2008c]{Arl:2008a}
Arlot, S. (2008c).
\newblock {$V$}-fold cross-validation improved: {$V$}-fold penalization.
\newblock arXiv:0802.0566v2.

\bibitem[Arlot and Celisse, 2009]{ArCe09}
Arlot, S. and Celisse, A. (2009).
\newblock {S}egmentation in the mean of heteroscedastic data via
  cross-validation.
\newblock arXiv:0902.3977v2.

\bibitem[Arlot and Massart, 2009]{Arl_Mas:2009:pente}
Arlot, S. and Massart, P. (2009).
\newblock Data-driven calibration of penalties for least-squares regression.
\newblock {\em J. Mach. Learn. Res.}, 10:245--279 (electronic).

\bibitem[Baraud, 2002]{Bar:2002}
Baraud, Y. (2002).
\newblock Model selection for regression on a random design.
\newblock {\em ESAIM Probab. Statist.}, 6:127--146 (electronic).

\bibitem[Barron et~al., 1999]{Bar_Bir_Mas:1999}
Barron, A., Birg{\'e}, L., and Massart, P. (1999).
\newblock Risk bounds for model selection via penalization.
\newblock {\em Probab. Theory Related Fields}, 113(3):301--413.

\bibitem[Bartlett et~al., 2002]{Bar_Bou_Lug:2002}
Bartlett, P.~L., Boucheron, S., and Lugosi, G. (2002).
\newblock Model selection and error estimation.
\newblock {\em Machine Learning}, 48:85--113.

\bibitem[Bartlett et~al., 2005]{Bar_Bou_Men:2005}
Bartlett, P.~L., Bousquet, O., and Mendelson, S. (2005).
\newblock Local {R}ademacher complexities.
\newblock {\em Ann. Statist.}, 33(4):1497--1537.

\bibitem[Bartlett and Mendelson, 2002]{Bar_Men:2002}
Bartlett, P.~L. and Mendelson, S. (2002).
\newblock Rademacher and {G}aussian complexities: risk bounds and structural
  results.
\newblock {\em J. Mach. Learn. Res.}, 3(Spec. Issue Comput. Learn.
  Theory):463--482.

\bibitem[Bellman and Dreyfus, 1962]{BeDr62}
Bellman, R.~E. and Dreyfus, S.~E. (1962).
\newblock {\em {A}pplied {D}ynamic {P}rogramming}.
\newblock Princeton.

\bibitem[Bengio and Grandvalet, 2004]{Ben_Gra:2004}
Bengio, Y. and Grandvalet, Y. (2004).
\newblock No unbiased estimator of the variance of {$K$}-fold cross-validation.
\newblock {\em J. Mach. Learn. Res.}, 5:1089--1105 (electronic).

\bibitem[Bhansali and Downham, 1977]{Bha_Dow:1977}
Bhansali, R.~J. and Downham, D.~Y. (1977).
\newblock Some properties of the order of an autoregressive model selected by a
  generalization of {A}kaike's {FPE} criterion.
\newblock {\em Biometrika}, 64(3):547--551.

\bibitem[Birg{\'e} and Massart, 2001]{Bir_Mas:2002}
Birg{\'e}, L. and Massart, P. (2001).
\newblock Gaussian model selection.
\newblock {\em J. Eur. Math. Soc. (JEMS)}, 3(3):203--268.

\bibitem[Birg{\'e} and Massart, 2007]{Bir_Mas:2006}
Birg{\'e}, L. and Massart, P. (2007).
\newblock Minimal penalties for {G}aussian model selection.
\newblock {\em Probab. Theory Related Fields}, 138(1-2):33--73.

\bibitem[Blanchard and Massart, 2006]{Bla_Mas:2006}
Blanchard, G. and Massart, P. (2006).
\newblock Discussion: ``{L}ocal {R}ademacher complexities and oracle
  inequalities in risk minimization'' [{A}nn. {S}tatist. {\bf 34} (2006), no.
  6, 2593--2656] by {V}. {K}oltchinskii.
\newblock {\em Ann. Statist.}, 34(6):2664--2671.

\bibitem[Boucheron et~al., 2005]{Bou_Bou_Lug:2005}
Boucheron, S., Bousquet, O., and Lugosi, G. (2005).
\newblock Theory of classification: a survey of some recent advances.
\newblock {\em ESAIM Probab. Stat.}, 9:323--375 (electronic).

\bibitem[Bousquet and Elisseff, 2002]{BoEl02}
Bousquet, O. and Elisseff, A. (2002).
\newblock {S}tability and {G}eneralization.
\newblock {\em J. Machine Learning Research}, 2:499--526.

\bibitem[Bowman, 1984]{Bowm84}
Bowman, A.~W. (1984).
\newblock {A}n alternative method of cross-validation for the smoothing of
  density estimates.
\newblock {\em Biometrika}, 71(2):353--360.

\bibitem[Breiman, 1996]{Bre:1996}
Breiman, L. (1996).
\newblock Heuristics of instability and stabilization in model selection.
\newblock {\em Ann. Statist.}, 24(6):2350--2383.

\bibitem[Breiman, 1998]{Brei96c}
Breiman, L. (1998).
\newblock Arcing classifiers.
\newblock {\em Ann. Statist.}, 26(3):801--849.
\newblock With discussion and a rejoinder by the author.

\bibitem[Breiman et~al., 1984]{Bre_etal:1984}
Breiman, L., Friedman, J.~H., Olshen, R.~A., and Stone, C.~J. (1984).
\newblock {\em Classification and regression trees}.
\newblock Wadsworth Statistics/Probability Series. Wadsworth Advanced Books and
  Software, Belmont, CA.

\bibitem[Breiman and Spector, 1992]{Bre_Spe:1992}
Breiman, L. and Spector, P. (1992).
\newblock Submodel selection and evaluation in regression. the x-random case.
\newblock {\em International Statistical Review}, 60(3):291--319.

\bibitem[Burman, 1989]{Bur:1989}
Burman, P. (1989).
\newblock A comparative study of ordinary cross-validation, {$v$}-fold
  cross-validation and the repeated learning-testing methods.
\newblock {\em Biometrika}, 76(3):503--514.

\bibitem[Burman, 1990]{Bur:1990}
Burman, P. (1990).
\newblock Estimation of optimal transformations using {$v$}-fold cross
  validation and repeated learning-testing methods.
\newblock {\em Sankhy\=a Ser. A}, 52(3):314--345.

\bibitem[Burman et~al., 1994]{Bur_Cho_Nol:1994}
Burman, P., Chow, E., and Nolan, D. (1994).
\newblock A cross-validatory method for dependent data.
\newblock {\em Biometrika}, 81(2):351--358.

\bibitem[Burman and Nolan, 1992]{Bur_Nol:1992}
Burman, P. and Nolan, D. (1992).
\newblock Data-dependent estimation of prediction functions.
\newblock {\em J. Time Ser. Anal.}, 13(3):189--207.

\bibitem[Burnham and Anderson, 2002]{Bur_And:2002}
Burnham, K.~P. and Anderson, D.~R. (2002).
\newblock {\em Model selection and multimodel inference}.
\newblock Springer-Verlag, New York, second edition.
\newblock A practical information-theoretic approach.

\bibitem[Cao and Golubev, 2006]{Cao_Gol:2006}
Cao, Y. and Golubev, Y. (2006).
\newblock On oracle inequalities related to smoothing splines.
\newblock {\em Math. Methods Statist.}, 15(4):398--414.

\bibitem[Celisse, 2008a]{Celi08}
Celisse, A. (2008a).
\newblock {D}ensity estimation via cross-validation: Model selection point of
  view.
\newblock Technical report, arXiv: 0811.0802.

\bibitem[Celisse, 2008b]{Cel:2008:phd}
Celisse, A. (2008b).
\newblock {\em {M}odel Selection Via Cross-Validation in Density Estimation,
  Regression and Change-Points Detection}.
\newblock PhD thesis, University Paris-Sud 11,
  \texttt{http://tel.archives-ouvertes.fr/tel-00346320/en/}.

\bibitem[Celisse and Robin, 2008]{CeRo08}
Celisse, A. and Robin, S. (2008).
\newblock {N}onparametric density estimation by exact leave-p-out
  cross-validation.
\newblock {\em Computational Statistics and Data Analysis}, 52(5):2350--2368.

\bibitem[Chow et~al., 1987]{ChGW87}
Chow, Y.~S., Geman, S., and Wu, L.~D. (1987).
\newblock Consistent cross-validated density estimation.
\newblock {\em Ann. Statist.}, 11:25--38.

\bibitem[Chu and Marron, 1991]{Chu_Mar:1991}
Chu, C.-K. and Marron, J.~S. (1991).
\newblock Comparison of two bandwidth selectors with dependent errors.
\newblock {\em Ann. Statist.}, 19(4):1906--1918.

\bibitem[Craven and Wahba, 1979]{Cra_Wah:1979}
Craven, P. and Wahba, G. (1979).
\newblock Smoothing noisy data with spline functions. {E}stimating the correct
  degree of smoothing by the method of generalized cross-validation.
\newblock {\em Numer. Math.}, 31(4):377--403.

\bibitem[Dalelane, 2005]{Dale05}
Dalelane, C. (2005).
\newblock Exact oracle inequality for sharp adaptive kernel density estimator.
\newblock Technical report, arXiv.

\bibitem[Daudin and Mary-Huard, 2008]{DaMa08}
Daudin, J.-J. and Mary-Huard, T. (2008).
\newblock {E}stimation of the conditional risk in classification: {T}he
  swapping method.
\newblock {\em Comput. Stat. Data Anal.}, 52(6):3220--3232.

\bibitem[Davison and Hall, 1992]{Dav_Hal:1992}
Davison, A.~C. and Hall, P. (1992).
\newblock On the bias and variability of bootstrap and cross-validation
  estimates of error rate in discrimination problems.
\newblock {\em Biometrika}, 79(2):279--284.

\bibitem[Devroye et~al., 1996]{Dev_Gyo_Lug:1996}
Devroye, L., Gy{\"o}rfi, L., and Lugosi, G. (1996).
\newblock {\em A probabilistic theory of pattern recognition}, volume~31 of
  {\em Applications of Mathematics (New York)}.
\newblock Springer-Verlag, New York.

\bibitem[Devroye and Wagner, 1979]{DeWa79}
Devroye, L. and Wagner, T.~J. (1979).
\newblock {D}istribution-{F}ree performance {B}ounds for {P}otential {F}unction
  {R}ules.
\newblock {\em IEEE Transaction in Information Theory}, 25(5):601--604.

\bibitem[Dietterich, 1998]{Die:1998}
Dietterich, T.~G. (1998).
\newblock Approximate statistical tests for comparing supervised classification
  learning algorithms.
\newblock {\em Neur. Comp.}, 10(7):1895--1924.

\bibitem[Efron, 1983]{Efr:1983}
Efron, B. (1983).
\newblock Estimating the error rate of a prediction rule: improvement on
  cross-validation.
\newblock {\em J. Amer. Statist. Assoc.}, 78(382):316--331.

\bibitem[Efron, 1986]{Efr:1986}
Efron, B. (1986).
\newblock How biased is the apparent error rate of a prediction rule?
\newblock {\em J. Amer. Statist. Assoc.}, 81(394):461--470.

\bibitem[Efron, 2004]{Efr:2004}
Efron, B. (2004).
\newblock The estimation of prediction error: covariance penalties and
  cross-validation.
\newblock {\em J. Amer. Statist. Assoc.}, 99(467):619--642.
\newblock With comments and a rejoinder by the author.

\bibitem[Efron and Morris, 1973]{EfMo73}
Efron, B. and Morris, C. (1973).
\newblock Combining possibly related estimation problems (with discussion).
\newblock {\em J. R. Statist. Soc. B}, 35:379.

\bibitem[Efron and Tibshirani, 1997]{Efr_Tib:1997}
Efron, B. and Tibshirani, R. (1997).
\newblock Improvements on cross-validation: the .632+ bootstrap method.
\newblock {\em J. Amer. Statist. Assoc.}, 92(438):548--560.

\bibitem[Fromont, 2007]{Fro:2007}
Fromont, M. (2007).
\newblock Model selection by bootstrap penalization for classification.
\newblock {\em Mach. Learn.}, 66(2--3):165--207.

\bibitem[Geisser, 1974]{Geis74}
Geisser, S. (1974).
\newblock {A} predictive approach to the random effect model.
\newblock {\em Biometrika}, 61(1):101--107.

\bibitem[Geisser, 1975]{Gei:1975}
Geisser, S. (1975).
\newblock The predictive sample reuse method with applications.
\newblock {\em J. Amer. Statist. Assoc.}, 70:320--328.

\bibitem[Girard, 1998]{Gir:1998}
Girard, D.~A. (1998).
\newblock Asymptotic comparison of (partial) cross-validation, {GCV} and
  randomized {GCV} in nonparametric regression.
\newblock {\em Ann. Statist.}, 26(1):315--334.

\bibitem[Gr{\"u}nwald, 2007]{Gru:2007}
Gr{\"u}nwald, P.~D. (2007).
\newblock {\em The {M}inimum {D}escription {L}ength {P}rinciple}.
\newblock MIT Press, Cambridge, MA, USA.

\bibitem[Gy{\"o}rfi et~al., 2002]{Gyo_etal:2002}
Gy{\"o}rfi, L., Kohler, M., Krzy{\.z}ak, A., and Walk, H. (2002).
\newblock {\em A distribution-free theory of nonparametric regression}.
\newblock Springer Series in Statistics. Springer-Verlag, New York.

\bibitem[Hall, 1983]{Hal:1983}
Hall, P. (1983).
\newblock Large sample optimality of least squares cross-validation in density
  estimation.
\newblock {\em Ann. Statist.}, 11(4):1156--1174.

\bibitem[Hall, 1987]{Hall87}
Hall, P. (1987).
\newblock {O}n {K}ullback-{L}eibler loss and density estimation.
\newblock {\em The Annals of Statistics}, 15(4):1491--1519.

\bibitem[Hall et~al., 1995]{Hal_Lah_Pol:1995}
Hall, P., Lahiri, S.~N., and Polzehl, J. (1995).
\newblock On bandwidth choice in nonparametric regression with both short- and
  long-range dependent errors.
\newblock {\em Ann. Statist.}, 23(6):1921--1936.

\bibitem[Hall et~al., 1992]{Hal_Mar_Par:1992}
Hall, P., Marron, J.~S., and Park, B.~U. (1992).
\newblock Smoothed cross-validation.
\newblock {\em Probab. Theory Related Fields}, 92(1):1--20.

\bibitem[Hall and Schucany, 1989]{Hal_Sch:1989}
Hall, P. and Schucany, W.~R. (1989).
\newblock A local cross-validation algorithm.
\newblock {\em Statist. Probab. Lett.}, 8(2):109--117.

\bibitem[H{\"a}rdle, 1984]{Haerd84}
H{\"a}rdle, W. (1984).
\newblock How to determine the bandwidth of some nonlinear smoothers in
  practice.
\newblock In {\em Robust and nonlinear time series analysis ({H}eidelberg,
  1983)}, volume~26 of {\em Lecture Notes in Statist.}, pages 163--184.
  Springer, New York.

\bibitem[H{\"a}rdle et~al., 1988]{Har_Hal_Mar:1988}
H{\"a}rdle, W., Hall, P., and Marron, J.~S. (1988).
\newblock How far are automatically chosen regression smoothing parameters from
  their optimum?
\newblock {\em J. Amer. Statist. Assoc.}, 83(401):86--101.
\newblock With comments by David W. Scott and Iain Johnstone and a reply by the
  authors.

\bibitem[Hart, 1994]{Har:1994}
Hart, J.~D. (1994).
\newblock Automated kernel smoothing of dependent data by using time series
  cross-validation.
\newblock {\em J. Roy. Statist. Soc. Ser. B}, 56(3):529--542.

\bibitem[Hart and Vieu, 1990]{Har_Vie:1990}
Hart, J.~D. and Vieu, P. (1990).
\newblock Data-driven bandwidth choice for density estimation based on
  dependent data.
\newblock {\em Ann. Statist.}, 18(2):873--890.

\bibitem[Hart and Wehrly, 1986]{Har_Weh:1986}
Hart, J.~D. and Wehrly, T.~E. (1986).
\newblock Kernel regression estimation using repeated measurements data.
\newblock {\em J. Amer. Statist. Assoc.}, 81(396):1080--1088.

\bibitem[Hastie et~al., 2001]{Has_Tib_Fri:2001}
Hastie, T., Tibshirani, R., and Friedman, J. (2001).
\newblock {\em The elements of statistical learning}.
\newblock Springer Series in Statistics. Springer-Verlag, New York.
\newblock Data mining, inference, and prediction.

\bibitem[Herzberg and Tsukanov, 1986]{HeTs86}
Herzberg, A.~M. and Tsukanov, A.~V. (1986).
\newblock A note on modifications of jackknife criterion for model selection.
\newblock {\em Utilitas Math.}, 29:209--216.

\bibitem[Herzberg, 1969]{Herz69}
Herzberg, P.~A. (1969).
\newblock {T}he parameters of cross-validation.
\newblock {\em Psychometrika}, 34:Monograph Supplement.

\bibitem[Hesterberg et~al., 2008]{Hes_etal:2008}
Hesterberg, T.~C., Choi, N.~H., Meier, L., and Fraley, C. (2008).
\newblock Least angle and l1 penalized regression: A review.
\newblock {\em Statistics Surveys}, 2:61--93 (electronic).

\bibitem[Hills, 1966]{Hill66}
Hills, M. (1966).
\newblock {A}llocation {R}ules and their {E}rror {R}ates.
\newblock {\em J. Royal Statist. Soc. Series B}, 28(1):1--31.

\bibitem[Huber, 1964]{Hube64}
Huber, P. (1964).
\newblock Robust estimation of a local parameter.
\newblock {\em Ann. Math. Statist.}, 35:73--101.

\bibitem[Hurvich and Tsai, 1989]{Hur_Tsa:1989}
Hurvich, C.~M. and Tsai, C.-L. (1989).
\newblock Regression and time series model selection in small samples.
\newblock {\em Biometrika}, 76(2):297--307.

\bibitem[John, 1971]{Joh:1971}
John, P. W.~M. (1971).
\newblock {\em Statistical design and analysis of experiments}.
\newblock The Macmillan Co., New York.

\bibitem[Jonathan et~al., 2000]{JoKM00}
Jonathan, P., Krzanowki, W.~J., and McCarthy, W.~V. (2000).
\newblock On the use of cross-validation to assess performance in multivariate
  prediction.
\newblock {\em Stat. and Comput.}, 10:209--229.

\bibitem[Kearns et~al., 1997]{KMNR97}
Kearns, M., Mansour, Y., Ng, A.~Y., and Ron, D. (1997).
\newblock {A}n {E}xperimental and {T}heoretical {C}omparison of {M}odel
  {S}election {M}ethods.
\newblock {\em Machine Learning}, 27:7--50.

\bibitem[Kearns and Ron, 1999]{KeRo99}
Kearns, M. and Ron, D. (1999).
\newblock {A}lgorithmic {S}tability and {S}anity-{C}heck {B}ounds for
  {L}eave-{O}ne-{O}ut {C}ross-{V}alidation.
\newblock {\em Neural Computation}, 11:1427--1453.

\bibitem[Koltchinskii, 2001]{Kol:2001}
Koltchinskii, V. (2001).
\newblock Rademacher penalties and structural risk minimization.
\newblock {\em IEEE Trans. Inform. Theory}, 47(5):1902--1914.

\bibitem[Koltchinskii, 2006]{Kol:2006}
Koltchinskii, V. (2006).
\newblock Local {R}ademacher complexities and oracle inequalities in risk
  minimization.
\newblock {\em Ann. Statist.}, 34(6):2593--2656.

\bibitem[Lachenbruch and Mickey, 1968]{LaMi68}
Lachenbruch, P.~A. and Mickey, M.~R. (1968).
\newblock {E}stimation of {E}rror {R}ates in {D}iscriminant {A}nalysis.
\newblock {\em Technometrics}, 10(1):1--11.

\bibitem[Larson, 1931]{Lars31}
Larson, S.~C. (1931).
\newblock {T}he shrinkage of the coefficient of multiple correlation.
\newblock {\em J. Edic. Psychol.}, 22:45--55.

\bibitem[Leung et~al., 1993]{LeMW93}
Leung, D., Marriott, F., and Wu, E. (1993).
\newblock Bandwidth selection in robust smoothing.
\newblock {\em J. Nonparametr. Statist.}, 2:333--339.

\bibitem[Leung, 2005]{Leu:2005}
Leung, D. H.-Y. (2005).
\newblock Cross-validation in nonparametric regression with outliers.
\newblock {\em Ann. Statist.}, 33(5):2291--2310.

\bibitem[Li, 1985]{Li85}
Li, K.-C. (1985).
\newblock From stein's unbiased risk estimates to the method of generalized
  cross validation.
\newblock {\em Ann. Statist.}, 13(4):1352--1377.

\bibitem[Li, 1987]{KCLi:1987}
Li, K.-C. (1987).
\newblock Asymptotic optimality for {$C\sb p$}, {$C\sb L$}, cross-validation
  and generalized cross-validation: discrete index set.
\newblock {\em Ann. Statist.}, 15(3):958--975.

\bibitem[Mallows, 1973]{Mal:1973}
Mallows, C.~L. (1973).
\newblock Some comments on ${C}_p$.
\newblock {\em Technometrics}, 15:661--675.

\bibitem[Markatou et~al., 2005]{Mar_etal:2005}
Markatou, M., Tian, H., Biswas, S., and Hripcsak, G. (2005).
\newblock Analysis of variance of cross-validation estimators of the
  generalization error.
\newblock {\em J. Mach. Learn. Res.}, 6:1127--1168 (electronic).

\bibitem[Massart, 2007]{Mas:2003:St-Flour}
Massart, P. (2007).
\newblock {\em Concentration inequalities and model selection}, volume 1896 of
  {\em Lecture Notes in Mathematics}.
\newblock Springer, Berlin.
\newblock Lectures from the 33rd Summer School on Probability Theory held in
  Saint-Flour, July 6--23, 2003, With a foreword by Jean Picard.

\bibitem[Molinaro et~al., 2005]{Mol_Sim_Pfe:2005}
Molinaro, A.~M., Simon, R., and Pfeiffer, R.~M. (2005).
\newblock Prediction error estimation: a comparison of resampling methods.
\newblock {\em Bioinformatics}, 21(15):3301--3307.

\bibitem[Mosteller and Tukey, 1968]{MoTu68}
Mosteller, F. and Tukey, J.~W. (1968).
\newblock {D}ata analysis, including statistics.
\newblock In Lindzey, G. and Aronson, E., editors, {\em {H}andbook of {S}ocial
  {P}sychology, {V}ol. 2}. Addison-Wesley.

\bibitem[Nadeau and Bengio, 2003]{NaBe03}
Nadeau, C. and Bengio, Y. (2003).
\newblock Inference for the generalization error.
\newblock {\em Machine Learning}, 52:239--281.

\bibitem[Nishii, 1984]{Nis:1984}
Nishii, R. (1984).
\newblock Asymptotic properties of criteria for selection of variables in
  multiple regression.
\newblock {\em Ann. Statist.}, 12(2):758--765.

\bibitem[Opsomer et~al., 2001]{Ops_Wan_Yan:2001}
Opsomer, J., Wang, Y., and Yang, Y. (2001).
\newblock Nonparametric regression with correlated errors.
\newblock {\em Statist. Sci.}, 16(2):134--153.

\bibitem[Picard and Cook, 1984]{Pic_Coo:1984}
Picard, R.~R. and Cook, R.~D. (1984).
\newblock Cross-validation of regression models.
\newblock {\em J. Amer. Statist. Assoc.}, 79(387):575--583.

\bibitem[Politis et~al., 1999]{Pol_Rom_Wol:1999}
Politis, D.~N., Romano, J.~P., and Wolf, M. (1999).
\newblock {\em Subsampling}.
\newblock Springer Series in Statistics. Springer-Verlag, New York.

\bibitem[Quenouille, 1949]{Que:1949}
Quenouille, M.~H. (1949).
\newblock Approximate tests of correlation in time-series.
\newblock {\em J. Roy. Statist. Soc. Ser. B.}, 11:68--84.

\bibitem[Ripley, 1996]{Ripl96}
Ripley, B.~D. (1996).
\newblock {\em Pattern Recognition and Neural Networks}.
\newblock Cambridge Univ. Press.

\bibitem[Rissanen, 1983]{Riss83}
Rissanen, J. (1983).
\newblock {U}niversal {P}rior for {I}ntegers and {E}stimation by {M}inimum
  {D}escription {L}ength.
\newblock {\em The Annals of Statistics}, 11(2):416--431.

\bibitem[Ronchetti et~al., 1997]{RoFB97}
Ronchetti, E., Field, C., and Blanchard, W. (1997).
\newblock Robust linear model selection by cross-validation.
\newblock {\em J. Amer. Statist. Assoc.}, 92:1017--1023.

\bibitem[Rudemo, 1982]{Rude82}
Rudemo, M. (1982).
\newblock {E}mpirical {C}hoice of {H}istograms and {K}ernel {D}ensity
  {E}stimators.
\newblock {\em Scandinavian Journal of Statistics}, 9:65--78.

\bibitem[Sauv\'e, 2009]{Sau:2006}
Sauv\'e, M. (2009).
\newblock Histogram selection in non gaussian regression.
\newblock {\em ESAIM: Probability and Statistics}, 13:70--86.

\bibitem[Schuster and Gregory, 1981]{ScGr81}
Schuster, E.~F. and Gregory, G.~G. (1981).
\newblock On the consistency of maximum likelihood nonparametric density
  estimators.
\newblock In Eddy, W.~F., editor, {\em Computer Science and Statistics:
  Proceedings of the 13th Symposium on the Interface}, pages 295--298.
  Springer-Verlag, New York.

\bibitem[Schwarz, 1978]{Sch:1978}
Schwarz, G. (1978).
\newblock Estimating the dimension of a model.
\newblock {\em Ann. Statist.}, 6(2):461--464.

\bibitem[Shao, 1993]{Sha:1993}
Shao, J. (1993).
\newblock Linear model selection by cross-validation.
\newblock {\em J. Amer. Statist. Assoc.}, 88(422):486--494.

\bibitem[Shao, 1996]{Sha:1996}
Shao, J. (1996).
\newblock Bootstrap model selection.
\newblock {\em J. Amer. Statist. Assoc.}, 91(434):655--665.

\bibitem[Shao, 1997]{Sha:1997}
Shao, J. (1997).
\newblock An asymptotic theory for linear model selection.
\newblock {\em Statist. Sinica}, 7(2):221--264.
\newblock With comments and a rejoinder by the author.

\bibitem[Shibata, 1984]{Shi:1984}
Shibata, R. (1984).
\newblock Approximate efficiency of a selection procedure for the number of
  regression variables.
\newblock {\em Biometrika}, 71(1):43--49.

\bibitem[Simon, 1971]{Simo71}
Simon, F. (1971).
\newblock {P}rediction methods in criminology.
\newblock volume~7.

\bibitem[Stone, 1984]{Ston84}
Stone, C. (1984).
\newblock {A}n asymptotically optimal window selection rule for kernel density
  estimates.
\newblock {\em The Annals of Statistics}, 12(4):1285--1297.

\bibitem[Stone, 1974]{Sto:1974}
Stone, M. (1974).
\newblock Cross-validatory choice and assessment of statistical predictions.
\newblock {\em J. Roy. Statist. Soc. Ser. B}, 36:111--147.
\newblock With discussion by G. A. Barnard, A. C. Atkinson, L. K. Chan, A. P.
  Dawid, F. Downton, J. Dickey, A. G. Baker, O. Barndorff-Nielsen, D. R. Cox,
  S. Giesser, D. Hinkley, R. R. Hocking, and A. S. Young, and with a reply by
  the authors.

\bibitem[Stone, 1977]{Sto:1977b}
Stone, M. (1977).
\newblock Asymptotics for and against cross-validation.
\newblock {\em Biometrika}, 64(1):29--35.

\bibitem[Sugiura, 1978]{Sug:1978}
Sugiura, N. (1978).
\newblock Further analysis of the data by akaike's information criterion and
  the finite corrections.
\newblock {\em Comm. Statist. A---Theory Methods}, 7(1):13--26.

\bibitem[Tibshirani, 1996]{Tibs96}
Tibshirani, R. (1996).
\newblock {R}egression {S}hrinkage and {S}election via the {L}asso.
\newblock {\em J. Royal Statist. Soc. Series B}, 58(1):267--288.

\bibitem[van~der Laan and Dudoit, 2003]{vdL_Dud:2003}
van~der Laan, M.~J. and Dudoit, S. (2003).
\newblock Unified cross-validation methodology for selection among estimators
  and a general cross-validated adaptive epsilon-net estimator: Finite sample
  oracle inequalities and examples.
\newblock Working Paper Series Working Paper 130, U.C. Berkeley Division of
  Biostatistics.
\newblock available at http://www.bepress.com/ucbbiostat/paper130.

\bibitem[van~der Laan et~al., 2004]{vdL_Dud_Kel:2004}
van~der Laan, M.~J., Dudoit, S., and Keles, S. (2004).
\newblock Asymptotic optimality of likelihood-based cross-validation.
\newblock {\em Stat. Appl. Genet. Mol. Biol.}, 3:Art. 4, 27 pp. (electronic).

\bibitem[van~der Laan et~al., 2006]{vdL_Dud_vdV:2006}
van~der Laan, M.~J., Dudoit, S., and van~der Vaart, A.~W. (2006).
\newblock The cross-validated adaptive epsilon-net estimator.
\newblock {\em Statist. Decisions}, 24(3):373--395.

\bibitem[van~der Vaart et~al., 2006]{vdV_Dud_vdL:2006}
van~der Vaart, A.~W., Dudoit, S., and van~der Laan, M.~J. (2006).
\newblock Oracle inequalities for multi-fold cross validation.
\newblock {\em Statist. Decisions}, 24(3):351--371.

\bibitem[van Erven et~al., 2008]{Erv_Gru_Roo:2008}
van Erven, T., Gr{\"u}nwald, P.~D., and de~Rooij, S. (2008).
\newblock Catching up faster by switching sooner: A prequential solution to the
  aic-bic dilemma.
\newblock arXiv:0807.1005.

\bibitem[Vapnik, 1982]{Vap:1982}
Vapnik, V. (1982).
\newblock {\em Estimation of dependences based on empirical data}.
\newblock Springer Series in Statistics. Springer-Verlag, New York.
\newblock Translated from the Russian by Samuel Kotz.

\bibitem[Vapnik, 1998]{Vap:1998}
Vapnik, V.~N. (1998).
\newblock {\em Statistical learning theory}.
\newblock Adaptive and Learning Systems for Signal Processing, Communications,
  and Control. John Wiley \& Sons Inc., New York.
\newblock A Wiley-Interscience Publication.

\bibitem[Vapnik and Chervonenkis, 1974]{Vap_Cer:1974}
Vapnik, V.~N. and Chervonenkis, A.~Y. (1974).
\newblock {\em Teoriya raspoznavaniya obrazov. {S}tatisticheskie problemy
  obucheniya}.
\newblock Izdat. ``Nauka'', Moscow.
\newblock Theory of Pattern Recognition (In Russian).

\bibitem[Wahba, 1975]{Wahb75}
Wahba, G. (1975).
\newblock {P}eriodic splines for spectral density estimation: {T}he use of
  cross validation for determining the degree of smoothing.
\newblock {\em Communications in Statistics}, 4:125--142.

\bibitem[Wahba, 1977]{Wahb77a}
Wahba, G. (1977).
\newblock {P}ractical {A}pproximate {S}olutions to {L}inear {O}perator
  {E}quations {W}hen the {D}ata are {N}oisy.
\newblock {\em SIAM Journal on Numerical Analysis}, 14(4):651--667.

\bibitem[Wegkamp, 2003]{Wegk03}
Wegkamp, M. (2003).
\newblock {M}odel selection in nonparametric regression.
\newblock {\em The Annals of Statistics}, 31(1):252--273.

\bibitem[Yang, 2005]{Yan:2005a}
Yang, Y. (2005).
\newblock Can the strengths of {AIC} and {BIC} be shared? {A} conflict between
  model indentification and regression estimation.
\newblock {\em Biometrika}, 92(4):937--950.

\bibitem[Yang, 2006]{Yan:2006}
Yang, Y. (2006).
\newblock Comparing learning methods for classification.
\newblock {\em Statist. Sinica}, 16(2):635--657.

\bibitem[Yang, 2007]{Yan:2007b}
Yang, Y. (2007).
\newblock Consistency of cross validation for comparing regression procedures.
\newblock {\em Ann. Statist.}, 35(6):2450--2473.

\bibitem[Zhang, 1993]{Zha:1993}
Zhang, P. (1993).
\newblock Model selection via multifold cross validation.
\newblock {\em Ann. Statist.}, 21(1):299--313.

\end{thebibliography}