The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have led to these recent results.
Keywords: pattern recognition, statistical learning theory, concentration inequalities, empirical processes, model selection
@article{PS_2005__9__323_0, author = {Boucheron, St\'ephane and Bousquet, Olivier and Lugosi, G\'abor}, title = {Theory of classification : a survey of some recent advances}, journal = {ESAIM: Probability and Statistics}, pages = {323--375}, publisher = {EDP-Sciences}, volume = {9}, year = {2005}, doi = {10.1051/ps:2005018}, mrnumber = {2182250}, zbl = {1136.62355}, language = {en}, url = {http://archive.numdam.org/articles/10.1051/ps:2005018/} }
TY - JOUR AU - Boucheron, Stéphane AU - Bousquet, Olivier AU - Lugosi, Gábor TI - Theory of classification : a survey of some recent advances JO - ESAIM: Probability and Statistics PY - 2005 SP - 323 EP - 375 VL - 9 PB - EDP-Sciences UR - http://archive.numdam.org/articles/10.1051/ps:2005018/ DO - 10.1051/ps:2005018 LA - en ID - PS_2005__9__323_0 ER -
%0 Journal Article %A Boucheron, Stéphane %A Bousquet, Olivier %A Lugosi, Gábor %T Theory of classification : a survey of some recent advances %J ESAIM: Probability and Statistics %D 2005 %P 323-375 %V 9 %I EDP-Sciences %U http://archive.numdam.org/articles/10.1051/ps:2005018/ %R 10.1051/ps:2005018 %G en %F PS_2005__9__323_0
Boucheron, Stéphane; Bousquet, Olivier; Lugosi, Gábor. Theory of classification : a survey of some recent advances. ESAIM: Probability and Statistics, Volume 9 (2005), pp. 323-375. doi : 10.1051/ps:2005018. http://archive.numdam.org/articles/10.1051/ps:2005018/
[1] Bounds on conditional probabilities with applications in multi-user communication. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete 34 (1976) 157-177. (correction in 39 (1977) 353-354). | Zbl
, and ,[2] The method of potential functions for the problem of restoring the characteristic of a function converter from randomly observed points. Automat. Remote Control 25 (1964) 1546-1556. | Zbl
, and ,[3] The probability problem of pattern recognition learning and the method of potential functions. Automat. Remote Control 25 (1964) 1307-1323. | Zbl
, and ,[4] Theoretical foundations of the potential function method in pattern recognition learning. Automat. Remote Control 25 (1964) 917-936. | Zbl
, and ,[5] Method of potential functions in the theory of learning machines. Nauka, Moscow (1970).
, and ,[6] A new look at the statistical model identification. IEEE Trans. Automat. Control 19 (1974) 716-723. | MR | Zbl
,[7] A remark on the Szarek-Talagrand theorem. Combin. Probab. Comput. 6 (1997) 139-144. | MR | Zbl
,[8] Scale-sensitive dimensions, uniform convergence, and learnability. J. ACM 44 (1997) 615-631. | MR | Zbl
, , and ,[9] Neural Network Learning: Theoretical Foundations. Cambridge University Press, Cambridge (1999). | MR | Zbl
and ,[10] Computational Learning Theory. Cambridge Tracts in Theoretical Computer Science (30). Cambridge University Press, Cambridge (1992). | MR | Zbl
and ,[11] A result of Vapnik with applications. Discrete Appl. Math. 47 (1993) 207-217. | Zbl
and ,[12] A Antos, L. Devroye and L. Györfi, Lower bounds for Bayes error estimation. IEEE Trans. Pattern Anal. Machine Intelligence 21 (1999) 643-645.
[13] Data-dependent margin-based generalization bounds for classification. J. Machine Learning Res. 3 (2002) 73-98. | Zbl
, , and ,[14] Strong minimax lower bounds for learning. Machine Learning 30 (1998) 31-56. | Zbl
and ,[15] Densité et dimension. Annales de l'Institut Fourier 33 (1983) 233-282. | Numdam | Zbl
,[16] Pac-Bayesian generic chaining, in Advances in Neural Information Processing Systems 16, L. Saul, S. Thrun and B. Schölkopf Eds., Cambridge, Mass., MIT Press (2004).
and ,[17] PAC-Bayesian Statistical Learning Theory. Ph.D. Thesis, Université Paris 6, Pierre et Marie Curie (2004).
,[18] Weighted sums of certain dependent random variables. Tohoku Math. J. 68 (1967) 357-367. | Zbl
,[19] Model selection for regression on a fixed design. Probability Theory and Related Fields 117 (2000) 467-493. | Zbl
,[20] Risks bounds for model selection via penalization. Probab. Theory Related Fields 113 (1999) 301-415. | Zbl
, and ,[21] Logically smooth density estimation. Technical Report TR 56, Department of Statistics, Stanford University (1985).
,[22] Complexity regularization with application to artificial neural networks, in Nonparametric Functional Estimation and Related Topics, G. Roussas Ed. NATO ASI Series, Kluwer Academic Publishers, Dordrecht (1991) 561-576. | Zbl
,[23] Minimum complexity density estimation. IEEE Trans. Inform. Theory 37 (1991) 1034-1054. | Zbl
and ,[24] Model selection and error estimation. Machine Learning 48 (2001) 85-113. | Zbl
, and ,[25] Localized Rademacher complexities. Ann. Statist. 33 (2005) 1497-1537. | Zbl
, and ,[26] Hardness results for neural network approximation problems. Theoret. Comput. Sci. 284 (2002) 53-66. | Zbl
and ,[27] Convexity, classification, and risk bounds. J. Amer. Statis. Assoc., to appear (2005). | MR | Zbl
, and ,[28] Vapnik-Chervonenkis dimension of neural nets, in Handbook Brain Theory Neural Networks, M.A. Arbib Ed. MIT Press, second edition. (2003) 1188-1192.
and ,[29] Rademacher and gaussian complexities: risk bounds and structural results. J. Machine Learning Res. 3 (2002) 463-482. | Zbl
and ,[30] Local Complexities for Empirical Risk Minimization, in Proc. of the 17th Annual Conference on Learning Theory (COLT), Springer (2004). | MR | Zbl
, and ,[31] Potential function algorithms for pattern recognition learning machines. Automat. Remote Control 25 (1964) 692-695. | Zbl
, and ,[32] Limitations of learning via embeddings in Euclidean half spaces. J. Machine Learning Res. 3 (2002) 441-461. | Zbl
, and ,[33] Probability inequalities for the sum of independent random variables. J. Amer. Statis. Assoc. 57 (1962) 33-45. | Zbl
,[34] The Theory of Probabilities. Gostehizdat Publishing House, Moscow (1946).
,[35] An alternative point of view on Lepski's method, in State of the art in probability and statistics (Leiden, 1999), Inst. Math. Statist., Beachwood, OH, IMS Lecture Notes Monogr. Ser. 36 (2001) 113-133.
,[36] Rates of convergence for minimum contrast estimators. Probab. Theory Related Fields 97 (1993) 113-150. | Zbl
and ,[37] From model selection to adaptive estimation, in Festschrift for Lucien Le Cam: Research papers in Probability and Statistics, E. Torgersen D. Pollard and G. Yang Eds., Springer, New York (1997) 55-87. | Zbl
and ,[38] Minimum contrast estimators on sieves: exponential bounds and rates of convergence. Bernoulli 4 (1998) 329-375. | Zbl
and ,[39] Statistical performance of support vector machines. Ann. Statist., to appear (2006). | MR | Zbl
, and ,[40] On the rates of convergence of regularized boosting classifiers. J. Machine Learning Res. 4 (2003) 861-894. | Zbl
, and ,[41] Learnability and the Vapnik-Chervonenkis dimension. J. ACM 36 (1989) 929-965. | Zbl
, , and ,[42] Poincaré's inequalities and Talagrands's concentration phenomenon for the exponential distribution. Probab. Theory Related Fields 107 (1997) 383-400. | Zbl
and ,[43] A training algorithm for optimal margin classifiers, in Proc. of the Fifth Annual ACM Workshop on Computational Learning Theory (COLT). Association for Computing Machinery, New York, NY (1992) 144-152.
, and ,[44] Moment inequalities for functions of independent random variables. Ann. Probab. 33 (2005) 514-560. | Zbl
, , and ,[45] A sharp concentration inequality with applications. Random Structures Algorithms 16 (2000) 277-292. | Zbl
, and ,[46] Concentration inequalities using the entropy method. Ann. Probab. 31 (2003) 1583-1614. | Zbl
, and ,[47] A Bennett concentration inequality and its application to suprema of empirical processes. C. R. Acad. Sci. Paris 334 (2002) 495-500. | Zbl
,[48] Concentration inequalities for sub-additive functions using the entropy method, in Stochastic Inequalities and Applications, C. Houdré E. Giné and D. Nualart Eds., Birkhauser (2003). | MR | Zbl
,[49] Stability and generalization. J. Machine Learning Res. 2 (2002) 499-526. | Zbl
and ,[50] Some local measures of complexity of convex hulls and generalization bounds, in Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT), Springer (2002) 59-73. | Zbl
, and ,[51] Arcing classifiers. Ann. Statist. 26 (1998) 801-849. | Zbl
,[52] Some infinite theory for predictor ensembles. Ann. Statist. 32 (2004) 1-11. | Zbl
,[53] Classification and Regression Trees. Wadsworth International, Belmont, CA (1984). | MR | Zbl
, , and ,[54] Boosting with the -loss: Regression and classification. J. Amer. Statis. Assoc. 98 (2004) 324-339. | Zbl
and ,[55] Machine learning with data dependent hypothesis classes. J. Machine Learning Res. 2 (2002) 335-358. | Zbl
, , and ,[56] Density estimation via exponential model selection. IEEE Trans. Inform. Theory 49 (2003) 2052-2060.
,[57] Randomized estimators and empirical complexity for pattern recognition and least square regression. Preprint PMA-677.
,[58] Statistical learning theory and stochastic optimization. École d'été de Probabilités de Saint-Flour XXXI. Springer-Verlag. Lect. Notes Math. 1851 (2004). | Zbl
,[59] Localized empirical complexity bounds and randomized estimators (2003). Preprint.
,[60] A graph-theoretic generalization of the Sauer-Shelah lemma. Discrete Appl. Math. 86 (1998) 27-35. | Zbl
and ,[61] Logistic regression, AdaBoost and Bregman distances. Machine Learning 48 (2002) 253-285. | Zbl
, and ,[62] Support vector networks. Machine Learning 20 (1995) 1-25. | Zbl
and ,[63] Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electronic Comput. 14 (1965) 326-334. | Zbl
,[64] Smoothing noisy data with spline functions: estimating the correct degree of smoothing by the method of generalized cross-validation. Numer. Math. 31 (1979) 377-403. | Zbl
and ,[65] An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge, UK (2000). | Zbl
and ,[66] Large-scale typicality of Markov sample paths and consistency of MDL order estimators. IEEE Trans. Inform. Theory 48 (2002) 1616-1628. | Zbl
,[67] The consistency of the BIC Markov order estimator. Ann. Statist. 28 (2000) 1601-1619. | Zbl
and ,[68] On the mathematical foundations of learning. Bull. Amer. Math. Soc. (2002) 1-50. | Zbl
and ,[69] Information inequalities and concentration of measure. Ann. Probab. 25 (1997) 927-939. | Zbl
,[70] Pattern Recognition: A Statistical Approach. Prentice-Hall, Englewood Cliffs, NJ (1982). | MR | Zbl
and ,[71] Automatic pattern recognition: A study of the probability of error. IEEE Trans. Pattern Anal. Machine Intelligence 10 (1988) 530-543. | Zbl
,[72] A Probabilistic Theory of Pattern Recognition. Springer-Verlag, New York (1996). | MR | Zbl
, and ,[73] Lower bounds in pattern recognition and learning. Pattern Recognition 28 (1995) 1011-1018.
and ,[74] Distribution-free inequalities for the deleted and holdout error estimates. IEEE Trans. Inform. Theory 25(2) (1979) 202-207. | Zbl
and ,[75] Distribution-free performance bounds for potential function rules. IEEE Trans. Inform. Theory 25(5) (1979) 601-604. | Zbl
and ,[76] Ideal spatial adaptation by wavelet shrinkage. Biometrika 81(3) (1994) 425-455. | Zbl
and ,[77] Pattern Classification and Scene Analysis. John Wiley, New York (1973). | Zbl
and ,[78] Pattern Classification. John Wiley and Sons (2000). | MR | Zbl
, and ,[79] Central limit theorems for empirical measures. Ann. Probab. 6 (1978) 899-929. | Zbl
,[80] Balls in do not cut all subsets of points. Advances Math. 31 (3) (1979) 306-308. | Zbl
,[81] Empirical processes, in École de Probabilité de St. Flour 1982. Lect. Notes Math. 1097 (1984). | Zbl
,[82] Universal Donsker classes and metric entropy. Ann. Probab. 15 (1987) 1306-1326. | Zbl
,[83] Uniform Central Limit Theorems. Cambridge University Press, Cambridge (1999). | MR | Zbl
,[84] Uniform and universal Glivenko-Cantelli classes. J. Theoret. Probab. 4 (1991) 485-510. | Zbl
, and ,[85] Bootstrap methods: another look at the jackknife. Ann. Statist. 7 (1979) 1-26. | Zbl
,[86] The jackknife, the bootstrap, and other resampling plans. SIAM, Philadelphia (1982). | MR | Zbl
,[87] An Introduction to the Bootstrap. Chapman and Hall, New York (1994). | MR | Zbl
and ,[88] A general lower bound on the number of examples needed for learning. Inform. Comput. 82 (1989) 247-261. | Zbl
, , and ,[89] Regularization networks and support vector machines, in Advances in Large Margin Classifiers, A.J. Smola, P.L. Bartlett B. Schölkopf and D. Schuurmans, Eds., Cambridge, MA, MIT Press. (2000) 171-203.
, and ,[90] On the trace of finite sets. J. Combin. Theory, Ser. A 34 (1983) 41-45. | Zbl
,[91] Boosting a weak learning algorithm by majority. Inform. Comput. 121 (1995) 256-285. | Zbl
,[92] Self bounding learning algorithms, in Proceedings of the 11th Annual Conference on Computational Learning Theory (1998) 127-135.
,[93] Generalization bounds for averaged classifiers (how to be a Bayesian without believing). Ann. Statist. (2004). | MR | Zbl
, and ,[94] A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55 (1997) 119-139. | Zbl
and ,[95] Additive logistic regression: a statistical view of boosting. Ann. Statist. 28 (2000) 337-374. | Zbl
, and ,[96] Some problems related to model selection: adaptive tests and bootstrap calibration of penalties. Thèse de doctorat, Université Paris-Sud (December 2003).
,[97] Introduction to Statistical Pattern Recognition. Academic Press, New York (1972). | MR | Zbl
,[98] Empirical processes and applications: an overview. Bernoulli 2 (1996) 1-28. | Zbl
,[99] Some limit theorems for empirical processes. Ann. Probab. 12 (1984) 929-989. | Zbl
and ,[100] Lectures on some aspects of the bootstrap, in Lectures on probability theory and statistics (Saint-Flour, 1996). Lect. Notes Math. 1665 (1997) 37-151. | Zbl
,[101] Bounding the Vapnik-Chervonenkis dimension of concept classes parametrized by real numbers. Machine Learning 18 (1995) 131-148. | Zbl
and ,[102] Abstract inference. John Wiley & Sons Inc., New York (1981). | MR | Zbl
,[103] Large sample optimality of least squares cross-validation in density estimation. Ann. Statist. 11 (1983) 1156-1174. | Zbl
,[104] The Elements of Statistical Learning. Springer Series in Statistics. Springer-Verlag, New York (2001). | MR | Zbl
, and ,[105] Decision theoretic generalizations of the pac model for neural nets and other learning applications. Inform. Comput. 100 (1992) 78-150. | Zbl
,[106] Sphere packing numbers for subsets of the boolean -cube with bounded Vapnik-Chervonenkis dimension. J. Combin. Theory, Ser. A 69 (1995) 217-232. | Zbl
,[107] Predicting functions from randomly drawn points, in Proc. of the 29th IEEE Symposium on the Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA (1988) 100-109.
, and ,[108] Algorithmic luckiness. J. Machine Learning Res. 3 (2003) 175-212. | Zbl
and ,[109] Probability inequalities for sums of bounded random variables. J. Amer. Statist. Assoc. 58 (1963) 13-30. | Zbl
,[110] The behavior of the maximum likelihood estimates under non-standard conditions, in Proc. Fifth Berkeley Symposium on Probability and Mathematical Statistics, Univ. California Press (1967) 221-233. | Zbl
,[111] Process consistency for adaboost. Ann. Statist. 32 (2004) 13-29. | Zbl
,[112] The densest hemisphere problem. Theoret. Comput. Sci. 6 (1978) 93-107. | Zbl
and ,[113] Function estimation and gaussian sequence models. Technical Report. Department of Statistics, Stanford University (2002).
,[114] Polynomial bounds for vc dimension of sigmoidal and general pfaffian neural networks. J. Comput. Syst. Sci. 54 (1997). | MR | Zbl
and ,[115] An experimental and theoretical comparison of model selection methods, in Proc. of the Eighth Annual ACM Workshop on Computational Learning Theory, Association for Computing Machinery, New York (1995) 21-30.
, , and ,[116] Algorithmic stability and sanity-check bounds for leave-one-out cross-validation. Neural Comput. 11(6) (1999) 1427-1453.
and ,[117] An Introduction to Computational Learning Theory. MIT Press, Cambridge, Massachusetts (1994). | MR
and ,[118] Fewnomials. Translations of Mathematical Monographs 88, American Mathematical Society (1991). | MR | Zbl
,[119] Strongly consistent code-based identification and order estimation for constrained finite-state model classes. IEEE Trans. Inform. Theory 39 (1993) 893-902. | Zbl
,[120] A correspondence between Bayesian estimation on stochastic processes and smoothing by splines. Ann. Math. Statist. 41 (1970) 495-502. | Zbl
and ,[121] Neural networks with quadratic vc dimension. J. Comput. Syst. Sci. 54 (1997). | MR | Zbl
and ,[122] On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition. Dokl. Akad. Nauk SSSR 114 (1957) 953-956. | Zbl
,[123] -entropy and -capacity of sets in functional spaces. Amer. Math. Soc. Transl., Ser. 2 17 (1961) 277-364. | Zbl
and ,[124] Rademacher penalties and structural risk minimization. IEEE Trans. Inform. Theory 47 (2001) 1902-1914. | Zbl
,[125] Local Rademacher complexities and oracle inequalities in risk minimization. Manuscript (September 2003). | Zbl
,[126] Rademacher processes and bounding the risk of function learning, in High Dimensional Probability II, E. Giné, D.M. Mason and J.A. Wellner, Eds. (2000) 443-459. | Zbl
and ,[127] Empirical margin distributions and bounding the generalization error of combined classifiers. Ann. Statist. 30 (2002). | MR | Zbl
and ,[128] Learning pattern classification - a survey. IEEE Trans. Inform. Theory 44 (1998) 2178-2206. Information Theory: 1948-1998. Commemorative special issue. | Zbl
, and ,[129] Almost-everywhere algorithmic stability and generalization error, in UAI-2002: Uncertainty in Artificial Intelligence (2002).
and ,[130] Bounds for averaging classifiers. CMU-CS 01-102, Carnegie Mellon University (2001).
and ,[131] Isoperimetry and gaussian analysis in Lectures on Probability Theory and Statistics, P. Bernard Ed., École d'Été de Probabilités de St-Flour XXIV-1994 (1996) 165-294. | Zbl
,[132] On Talagrand's deviation inequalities for product measures. ESAIM: PS 1 (1997) 63-87. | Numdam | Zbl
,[133] Probability in Banach Space. Springer-Verlag, New York (1991). | MR | Zbl
and ,[134] The importance of convexity in learning with squared loss. IEEE Trans. Inform. Theory 44 (1998) 1974-1980. | Zbl
, and ,[135] Optimal spatial adaptation to inhomogeneous smoothness: an approach based on kernel estimates with variable bandwidth selectors. Ann. Statist. 25 (1997) 929-947. | Zbl
, and ,[136] A problem of adaptive estimation in Gaussian white noise. Teor. Veroyatnost. i Primenen. 35 (1990) 459-470. | Zbl
,[137] Asymptotically minimax adaptive estimation. I. Upper bounds. Optimally adaptive estimates. Teor. Veroyatnost. i Primenen. 36 (1991) 645-659. | Zbl
,[138] Improved bounds on the sample complexity of learning. J. Comput. Syst. Sci. 62 (2001) 516-527. | Zbl
, and ,[139] A note on margin-based loss functions in classification. Technical Report 1029r, Department of Statistics, University Wisconsin, Madison (1999). | Zbl
,[140] Some asymptotic properties of the support vector machine. Technical Report 1044r, Department of Statistics, University of Wisconsin, Madison (1999).
,[141] Support vector machines and the bayes rule in classification. Data Mining and Knowledge Discovery 6 (2002) 259-275.
,[142] Model selection using Rademacher penalization, in Proceedings of the Second ICSC Symposia on Neural Computation (NC2000). ICSC Adademic Press (2000).
,[143] Concentration for locally acting permutations. Discrete Math. 265 (2003) 159-171. | Zbl
and ,[144] Pattern classification and learning theory, in Principles of Nonparametric Learning, L. Györfi Ed., Springer, Wien (2002) 5-62.
,[145] Adaptive model selection using empirical complexities. Ann. Statist. 27 (1999) 1830-1864. | Zbl
and ,[146] On the Bayes-risk consistency of regularized boosting methods. Ann. Statist. 32 (2004) 30-55. | Zbl
and ,[147] Complexity regularization via localized random penalties. Ann. Statist. 2 (2004) 1679-1697. | Zbl
and ,[148] Concept learning using complexity regularization. IEEE Trans. Inform. Theory 42 (1996) 48-54. | Zbl
and ,[149] Finiteness results for sigmoidal “neural” networks, in Proc. of the 25th Annual ACM Symposium on the Theory of Computing, Association of Computing Machinery, New York (1993) 325-334.
and ,[150] Some comments on . Technometrics 15 (1997) 661-675. | Zbl
,[151] Smooth discrimination analysis. Ann. Statist. 27(6) (1999) 1808-1829. | Zbl
and ,[152] Weak learners and improved convergence rate in boosting, in Advances in Neural Information Processing Systems 13: Proc. NIPS'2000 (2001).
and ,[153] The consistency of greedy algorithms for classification, in Proceedings of the 15th Annual Conference on Computational Learning Theory (2002). | MR | Zbl
, and ,[154] A simple proof of the blowing-up lemma. IEEE Trans. Inform. Theory 32 (1986) 445-446. | Zbl
,[155] Bounding -distance by informational divergence: a way to prove measure concentration. Ann. Probab. 24 (1996) 857-866. | Zbl
,[156] A measure concentration inequality for contracting Markov chains. Geometric Functional Analysis 6 (1996) 556-571. Erratum: 7 (1997) 609-613. | Zbl
,[157] Functional gradient techniques for combining hypotheses, in Advances in Large Margin Classifiers, A.J. Smola, P.L. Bartlett, B. Schölkopf and D. Schuurmans Eds., MIT Press, Cambridge, MA (1999) 221-247.
, , and ,[158] Optimal constants for Hoeffding type inequalities. Technical report, Mathematiques, Université de Paris-Sud, Report 98.86, 1998.
,[159] About the constants in Talagrand's concentration inequalities for empirical processes. Ann. Probab. 28 (2000) 863-884. | Zbl
,[160] Some applications of concentration inequalities to statistics. Ann. Fac. Sci. Toulouse IX (2000) 245-303. | Numdam | Zbl
,[161] École d'Eté de Probabilité de Saint-Flour XXXIII, chapter Concentration inequalities and model selection, LNM. Springer-Verlag (2003).
,[162] Risk bounds for statistical learning, Ann. Statist., to appear. | MR | Zbl
and ,[163] Some pac-Bayesian theorems, in Proc. of the 11th Annual Conference on Computational Learning Theory, ACM Press (1998) 230-234.
,[164] MR
, pac-Bayesian model averaging, in Proc. of the 12th Annual Conference on Computational Learning Theory. ACM Press (1999). |[165] -Bayesian stochastic model selection. Machine Learning 51 (2003) 5-21. | Zbl
,[166] On the method of bounded differences, in Surveys in Combinatorics 1989, Cambridge University Press, Cambridge (1989) 148-188. | Zbl
,[167] Concentration, in Probabilistic Methods for Algorithmic Discrete Mathematics, M. Habib, C. McDiarmid, J. Ramirez-Alfonsin and B. Reed Eds., Springer, New York (1998) 195-248. | Zbl
,[168] Concentration for independent permutations. Combin. Probab. Comput. 2 (2002) 163-178. | Zbl
,[169] Discriminant Analysis and Statistical Pattern Recognition. John Wiley, New York (1992). | MR | Zbl
,[170] Improving the sample complexity using global data. IEEE Trans. Inform. Theory 48 (2002) 1977-1991. | Zbl
,[171] A few notes on statistical learning theory, in Advanced Lectures in Machine Learning. Lect. Notes Comput. Sci. 2600, S. Mendelson and A. Smola Eds., Springer (2003) 1-40. | Zbl
,[172] On the importance of “small” coordinate projections. J. Machine Learning Res. 5 (2004) 219-238.
and ,[173] Entropy and the combinatorial dimension. Inventiones Mathematicae 152 (2003) 37-55. | Zbl
and ,[174] Asymptotic theory of finite-dimensional normed spaces, Springer-Verlag, New York (1986). | MR
and ,[175] Machine Learning: A Theoretical Approach, Morgan Kaufmann, San Mateo, CA (1991). | MR
,[176] A note on Talagrand's concentration inequality. Electron. Comm. Probab. 6 (2001). | Zbl
,[177] Some extensions of an inequality of Vapnik and Chervonenkis. Electron. Comm. Probab. 7 (2002). | MR | Zbl
,[178] Symmetrization approach to concentration inequalities for empirical processes. Ann. Probab. 31 (2003) 2068-2081. | Zbl
,[179] General conditions for predictivity in learning theory. Nature 428 (2004) 419-422.
, , and ,[180] Convergence of Stochastic Processes, Springer-Verlag, New York (1984). | MR | Zbl
,[181] Uniform ratio limit theorems for empirical processes. Scand. J. Statist. 22 (1995) 271-278. | Zbl
,[182] Measuring mass concentrations and estimating density contour clusters-an excess mass approach. Ann. Statist. 23(3) (1995) 855-881. | Zbl
,[183] Inégalités de concentration pour les processus empiriques de classes de parties. Probab. Theory Related Fields 119 (2001) 163-175. | Zbl
,[184] Une inegalité de Bennett pour les maxima de processus empiriques, in Colloque en l'honneur de J. Bretagnolle, D. Dacunha-Castelle et I. Ibragimov, Annales de l'Institut Henri Poincaré (2001). | Numdam | Zbl
,[185] Pattern Recognition and Neural Networks, Cambridge University Press (1996). | MR | Zbl
,[186] A finite sample distribution-free performance bound for local discrimination rules. Ann. Statist. 6 (1978) 506-514. | Zbl
and ,[187] Combinatorics of random processes and sections of convex bodies. Ann. Math, to appear (2004). | MR | Zbl
, ,[188] On the density of families of sets. J. Combin. Theory, Ser A 13 (1972) 145-147. | Zbl
,[189] The strength of weak learnability. Machine Learning 5 (1990) 197-227. | Zbl
,[190] Boosting the margin: a new explanation for the effectiveness of voting methods. Ann. Statist. 26 (1998) 1651-1686. | Zbl
, , and ,[191] Learning with Kernels. MIT Press, Cambridge, MA (2002).
and ,[192] Characterizing rational versus exponential learning curves, in Computational Learning Theory: Second European Conference. EuroCOLT'95, Springer-Verlag (1995) 272-286.
,[193] Fast rates for support vector machines. Los Alamos National Laboratory Technical Report LA-UR 03-9117 (2003).
and ,[194] PAC-Bayesian generalisation error bounds for gaussian process classification. J. Machine Learning Res. 3 (2002) 233-269. | Zbl
,[195] Structural risk minimization over data-dependent hierarchies. IEEE Trans. Inform. Theory 44 (1998) 1926-1940. | Zbl
, , and ,[196] A combinatorial problem: Stability and order for models and theories in infinity languages. Pacific J. Mathematics 41 (1972) 247-261. | Zbl
,[197] Empirical Processes with Applications in Statistics. Wiley, New York (1986). | MR
and ,[198] General lower bounds on the number of examples needed for learning probabilistic concepts, in Proc. of the Sixth Annual ACM Conference on Computational Learning Theory, Association for Computing Machinery, New York (1993) 402-412.
,[199] Advances in Large Margin Classifiers. MIT Press, Cambridge, MA (2000). | MR | Zbl
, , and ,[200] The connection between regularization operators and support vector kernels. Neural Networks 11 (1998) 637-649.
, and ,[201] Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification. IEEE Trans. Neural Networks 1 (1990) 111-121.
,[202] Existence of submatrices with all possible columns. J. Combin. Theory, Ser. A 28 (1978) 84-88. | Zbl
,[203] On the influence of the kernel on the consistency of support vector machines. J. Machine Learning Res. (2001) 67-93. | Zbl
,[204] Consistency of support vector machines and other regularized kernel machines. IEEE Trans. Inform. Theory 51 (2005) 128-142.
,[205] Support vector machines are universally consistent. J. Complexity 18 (2002) 768-791. | Zbl
,[206] On the optimal parameter choice in -support vector machines. IEEE Trans. Pattern Anal. Machine Intelligence 25 (2003) 1274-1284.
,[207] Sparseness of support vector machines. J. Machine Learning Res. 4 (2003) 1071-1105. | Zbl
,[208] On the convexified Sauer-Shelah theorem. J. Combin. Theory, Ser. B 69 (1997) 183-192. | Zbl
and ,[209] The Glivenko-Cantelli problem. Ann. Probab. 15 (1987) 837-870. | Zbl
,[210] Sharper bounds for Gaussian and empirical processes. Ann. Probab. 22 (1994) 28-76. | Zbl
,[211] Concentration of measure and isoperimetric inequalities in product spaces. Publications Mathématiques de l'I.H.E.S. 81 (1995) 73-205. | Numdam | Zbl
,[212] The Glivenko-Cantelli problem, ten years later. J. Theoret. Probab. 9 (1996) 371-384. | Zbl
,[213] Majorizing measures: the generic chaining. Ann. Probab. 24 (1996) 1049-1103. (Special Invited Paper). | Zbl
,[214] New concentration inequalities in product spaces. Inventiones Mathematicae 126 (1996) 505-563. | Zbl
,[215] A new look at independence. Ann. Probab. 24 (1996) 1-34. (Special Invited Paper). | Zbl
,[216] Vapnik-Chervonenkis type conditions and uniform Donsker classes of functions. Ann. Probab. 31 (2003) 1565-1582. | Zbl
,[217] The generic chaining: upper and lower bounds for stochastic processes. Springer-Verlag, New York (2005). | MR | Zbl
,[218] On nonparametric estimation of density level sets. Ann. Stat. 25 (1997) 948-969. | Zbl
.[219] Optimal aggregation of classifiers in statistical learning. Ann. Statist. 32 (2004) 135-166. | Zbl
,[220] Introduction à l'estimation non-paramétrique. Springer (2004). | Zbl
,[221] Square root penalty: adaptation to the margin in classification and in edge estimation. Ann. Statist., to appear (2005). | MR | Zbl
and ,[222] A new approach to least-squares estimation, with applications. Ann. Statist. 15 (1987) 587-602. | Zbl
,[223] Estimating a regression function. Ann. Statist. 18 (1990) 907-924. | Zbl
,[224] Empirical Processes in M-Estimation. Cambridge University Press, Cambridge, UK (2000). | MR
,[225] Weak convergence and empirical processes. Springer-Verlag, New York (1996). | MR | Zbl
and ,[226] Pattern recognition using generalized portrait method. Automat. Remote Control 24 (1963) 774-780.
and ,[227] Estimation of Dependencies Based on Empirical Data. Springer-Verlag, New York (1982). | MR | Zbl
,[228] The Nature of Statistical Learning Theory. Springer-Verlag, New York (1995). | MR | Zbl
,[229] Statistical Learning Theory. John Wiley, New York (1998). | MR | Zbl
,[230] On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16 (1971) 264-280. | Zbl
and ,[231] Theory of Pattern Recognition. Nauka, Moscow (1974). (in Russian); German translation: Theorie der Zeichenerkennung, Akademie Verlag, Berlin (1979). | MR
and ,[232] Necessary and sufficient conditions for the uniform convergence of means to their expectations. Theory Probab. Appl. 26 (1981) 821-832. | Zbl
and ,[233] A Theory of Learning and Generalization. Springer, New York (1997). | MR | Zbl
,[234] On the infeasibility of training neural networks with small mean squared error. IEEE Trans. Inform. Theory 44 (1998) 2892-2900. | Zbl
,[235] Model selection in nonparametric regression. Ann. Statist. 31(1) (2003) 252-273. | Zbl
,[236] Some special Vapnik-Chervonenkis classes. Discrete Math. 33 (1981) 313-318. | Zbl
and ,[237] Minimax nonparametric classification. I. Rates of convergence. IEEE Trans. Inform. Theory 45(7) (1999) 2271-2284. | Zbl
,[238] Minimax nonparametric classification. II. Model selection for adaptation. IEEE Trans. Inform. Theory 45(7) (1999) 2285-2292. | Zbl
,[239] Adaptive estimation in pattern recognition by combining different procedures. Statistica Sinica 10 (2000) 1069-1089. | Zbl
,[240] Exponential bounds for large deviations. Theory Probab. Appl. 19 (1974) 154-155. | Zbl
,[241] Exponential inequalities for sums of random vectors. J. Multivariate Anal. 6 (1976) 473-499. | Zbl
,[242] Statistical behavior and consistency of classification methods based on convex risk minimization. Ann. Statist. 32 (2004) 56-85. | Zbl
,[243] Capacity of reproducing kernel spaces in learning theory. IEEE Trans. Inform. Theory 49 (2003) 1743-1752.
,Cited by Sources: