{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:47:11Z","timestamp":1785520031582,"version":"3.56.0"},"publisher-location":"Berlin, Heidelberg","reference-count":63,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540752240","type":"print"},{"value":"9783540752257","type":"electronic"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-75225-7_5","type":"book-chapter","created":{"date-parts":[[2007,10,10]],"date-time":"2007-10-10T12:46:43Z","timestamp":1192020403000},"page":"13-31","source":"Crossref","is-referenced-by-count":299,"title":["A Hilbert Space Embedding for Distributions"],"prefix":"10.1007","author":[{"given":"Alex","family":"Smola","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur","family":"Gretton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Sch\u00f6lkopf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V. Vapnik","year":"1995","unstructured":"Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)"},{"key":"5_CR2","volume-title":"Learning with Kernels","author":"B. Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf, B., Smola, A.: Learning with Kernels. MIT Press, Cambridge (2002)"},{"key":"5_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0907-3","volume-title":"Learning to Classify Text Using Support Vector Machines: Methods, Theory, and Algorithms","author":"T. Joachims","year":"2002","unstructured":"Joachims, T.: Learning to Classify Text Using Support Vector Machines: Methods, Theory, and Algorithms. Kluwer Academic Publishers, Boston (2002)"},{"key":"5_CR4","volume-title":"Gaussian Processes for Machine Learning","author":"C.E. Rasmussen","year":"2006","unstructured":"Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)"},{"key":"5_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611","volume-title":"Elements of Information Theory","author":"T.M. Cover","year":"1991","unstructured":"Cover, T.M., Thomas, J.A.: Elements of Information Theory. John Wiley and Sons, New York (1991)"},{"key":"5_CR6","unstructured":"Amari, S., Nagaoka, H.: Methods of Information Geometry. Oxford University Press (1993)"},{"key":"5_CR7","unstructured":"Krause, A., Guestrin, C.: Near-optimal nonmyopic value of information in graphical models. In: Uncertainty in Artificial Intelligence UAI 2005 (2005)"},{"key":"5_CR8","first-page":"617","volume-title":"Advances in Neural Information Processing Systems","author":"N. Slonim","year":"2000","unstructured":"Slonim, N., Tishby, N.: Agglomerative information bottleneck. In: Solla, S.A., Leen, T.K., M\u00fcller, K.R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a012, pp. 617\u2013623. MIT Press, Cambridge (2000)"},{"issue":"6","key":"5_CR9","doi-asserted-by":"publisher","first-page":"66123","DOI":"10.1103\/PhysRevE.70.066123","volume":"70","author":"H. St\u00f6gbauer","year":"2004","unstructured":"St\u00f6gbauer, H., Kraskov, A., Astakhov, S., Grassberger, P.: Least dependent component analysis based on mutual information. Phys. Rev. E\u00a070(6), 66123 (2004)","journal-title":"Phys. Rev. E"},{"key":"5_CR10","volume-title":"Neural Information Processing Systems","author":"I. Nemenman","year":"2002","unstructured":"Nemenman, I., Shafee, F., Bialek, W.: Entropy and inference, revisited. In: Neural Information Processing Systems, vol.\u00a014, MIT Press, Cambridge (2002)"},{"key":"5_CR11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682","volume-title":"Kernel Methods for Pattern Analysis","author":"J. Shawe-Taylor","year":"2004","unstructured":"Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)"},{"key":"5_CR12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4057.001.0001","volume-title":"Kernel Methods in Computational Biology","author":"B. Sch\u00f6lkopf","year":"2004","unstructured":"Sch\u00f6lkopf, B., Tsuda, K., Vert, J.P.: Kernel Methods in Computational Biology. MIT Press, Cambridge (2004)"},{"key":"5_CR13","unstructured":"Hofmann, T., Sch\u00f6lkopf, B., Smola, A.J.: A review of kernel methods in machine learning. Technical Report 156, Max-Planck-Institut f\u00fcr biologische Kybernetik (2006)"},{"key":"5_CR14","unstructured":"Steinwart, I.: The influence of the kernel on the consistency of support vector machines. Journal of Machine Learning Research\u00a02 (2002)"},{"key":"5_CR15","first-page":"73","volume":"5","author":"K. Fukumizu","year":"2004","unstructured":"Fukumizu, K., Bach, F.R., Jordan, M.I.: Dimensionality reduction for supervised learning with reproducing kernel hilbert spaces. J. Mach. Learn. Res.\u00a05, 73\u201399 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR16","volume-title":"Advances in Neural Information Processing Systems","author":"A. Gretton","year":"2007","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., Smola, A.J.: A kernel method for the two-sample-problem. In: Sch\u00f6lkopf, B., Platt, J., Hofmann, T. (eds.) Advances in Neural Information Processing Systems, vol.\u00a019, MIT Press, Cambridge (2007)"},{"key":"5_CR17","first-page":"139","volume-title":"Proc. Annual Conf. Computational Learning Theory","author":"Y. Altun","year":"2006","unstructured":"Altun, Y., Smola, A.: Unifying divergence minimization and statistical inference via convex duality. In: Simon, H., Lugosi, G. (eds.) Proc. Annual Conf. Computational Learning Theory, pp. 139\u2013153. Springer, Heidelberg (2006)"},{"key":"5_CR18","first-page":"463","volume":"3","author":"P.L. Bartlett","year":"2002","unstructured":"Bartlett, P.L., Mendelson, S.: Rademacher and gaussian complexities: Risk bounds and structural results. J. Mach. Learn. Res.\u00a03, 463\u2013482 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1109\/18.930926","volume":"47","author":"V. Koltchinskii","year":"2001","unstructured":"Koltchinskii, V.: Rademacher penalties and structural risk minimization. IEEE Trans. Inform. Theory\u00a047, 1902\u20131914 (2001)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"2","key":"5_CR20","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1137\/1116025","volume":"16","author":"V. Vapnik","year":"1971","unstructured":"Vapnik, V., Chervonenkis, A.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl.\u00a016(2), 264\u2013281 (1971)","journal-title":"Theory Probab. Appl."},{"issue":"3","key":"5_CR21","first-page":"543","volume":"26","author":"V. Vapnik","year":"1981","unstructured":"Vapnik, V., Chervonenkis, A.: The necessary and sufficient conditions for the uniform convergence of averages to their expected values. Teoriya Veroyatnostei i Ee Primeneniya\u00a026(3), 543\u2013564 (1981)","journal-title":"Teoriya Veroyatnostei i Ee Primeneniya"},{"key":"5_CR22","unstructured":"Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Technical Report 649, UC Berkeley, Department of Statistics (September 2003)"},{"key":"5_CR23","unstructured":"Ravikumar, P., Lafferty, J.: Variational chernoff bounds for graphical models. In: Uncertainty in Artificial Intelligence UAI 2004 (2004)"},{"key":"5_CR24","unstructured":"Altun, Y., Smola, A.J., Hofmann, T.: Exponential families for conditional random fields. In: Uncertainty in Artificial Intelligence (UAI), Arlington, Virginia, pp. 2\u20139. AUAI Press (2004)"},{"key":"5_CR25","unstructured":"Hammersley, J.M., Clifford, P.E.: Markov fields on finite graphs and lattices (unpublished manuscript, 1971)"},{"issue":"B","key":"5_CR26","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1111\/j.2517-6161.1974.tb00999.x","volume":"36","author":"J. Besag","year":"1974","unstructured":"Besag, J.: Spatial interaction and the statistical analysis of lattice systems (with discussion). J. Roy. Stat. Soc. Ser. B Stat. Methodol.\u00a036(B), 192\u2013326 (1974)","journal-title":"J. Roy. Stat. Soc. Ser. B Stat. Methodol."},{"key":"5_CR27","unstructured":"Hein, M., Bousquet, O.: Hilbertian metrics and positive definite kernels on probability measures. In: Ghahramani, Z., Cowell, R. (eds.) Proc. of AI & Statistics, vol.\u00a010 (2005)"},{"key":"5_CR28","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316481","volume-title":"Approximation Theorems of Mathematical Statistics","author":"R. Serfling","year":"1980","unstructured":"Serfling, R.: Approximation Theorems of Mathematical Statistics. Wiley, New York (1980)"},{"key":"5_CR29","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","volume":"58","author":"W. Hoeffding","year":"1963","unstructured":"Hoeffding, W.: Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association\u00a058, 13\u201330 (1963)","journal-title":"Journal of the American Statistical Association"},{"key":"5_CR30","volume-title":"Advances in Neural Information Processing Systems 19","author":"A. Gretton","year":"2007","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., Smola, A.: A kernel method for the two-sample-problem. In: Advances in Neural Information Processing Systems 19, MIT Press, Cambridge (2007)"},{"key":"5_CR31","first-page":"148","volume-title":"Surveys in Combinatorics","author":"C. McDiarmid","year":"1969","unstructured":"McDiarmid, C.: On the method of bounded differences. In: Surveys in Combinatorics, pp. 148\u2013188. Cambridge University Press, Cambridge (1969)"},{"key":"5_CR32","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1006\/jmva.1994.1033","volume":"50","author":"N. Anderson","year":"1994","unstructured":"Anderson, N., Hall, P., Titterington, D.: Two-sample test statistics for measuring discrepancies between two multivariate probability density functions using kernel-based density estimates. Journal of Multivariate Analysis\u00a050, 41\u201354 (1994)","journal-title":"Journal of Multivariate Analysis"},{"key":"5_CR33","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198572237.001.0001","volume-title":"Probability and Random Processes","author":"G.R. Grimmet","year":"2001","unstructured":"Grimmet, G.R., Stirzaker, D.R.: Probability and Random Processes, 3rd edn. Oxford University Press, Oxford (2001)","edition":"3"},{"issue":"2","key":"5_CR34","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1214\/aos\/1176348650","volume":"20","author":"M. Arcones","year":"1992","unstructured":"Arcones, M., Gin\u00e9, E.: On the bootstrap of u and v statistics. The Annals of Statistics\u00a020(2), 655\u2013674 (1992)","journal-title":"The Annals of Statistics"},{"key":"5_CR35","unstructured":"Johnson, N.L., Kotz, S., Balakrishnan, N.: Continuous Univariate Distributions, 2nd edn., vol. 1. John Wiley and Sons, Chichester (1994)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.P., Sch\u00f6lkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics\u00a022(14), e49\u2013e57 (2006)","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"5_CR37","volume-title":"Advances in Neural Information Processing Systems","author":"J. Huang","year":"2007","unstructured":"Huang, J., Smola, A., Gretton, A., Borgwardt, K., Sch\u00f6lkopf, B.: Correcting sample selection bias by unlabeled data. In: Sch\u00f6lkopf, B., Platt, J., Hofmann, T. (eds.) Advances in Neural Information Processing Systems, vol.\u00a019, MIT Press, Cambridge (2007)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Shimodaira, H.: Improving predictive inference under convariance shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference\u00a090 (2000)","DOI":"10.1016\/S0378-3758(00)00115-4"},{"issue":"6","key":"5_CR39","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1162\/neco.1992.4.6.888","volume":"4","author":"L. Bottou","year":"1992","unstructured":"Bottou, L., Vapnik, V.N.: Local learning algorithms. Neural Computation\u00a04(6), 888\u2013900 (1992)","journal-title":"Neural Computation"},{"key":"5_CR40","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/0165-1684(94)90029-9","volume":"36","author":"P. Comon","year":"1994","unstructured":"Comon, P.: Independent component analysis, a new concept? Signal Processing\u00a036, 287\u2013314 (1994)","journal-title":"Signal Processing"},{"key":"5_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0898-1221(00)00101-2","volume":"39","author":"T.W. Lee","year":"2000","unstructured":"Lee, T.W., Girolami, M., Bell, A., Sejnowski, T.: A unifying framework for independent component analysis. Comput. Math. Appl.\u00a039, 1\u201321 (2000)","journal-title":"Comput. Math. Appl."},{"key":"5_CR42","first-page":"1","volume":"3","author":"F.R. Bach","year":"2002","unstructured":"Bach, F.R., Jordan, M.I.: Kernel independent component analysis. J. Mach. Learn. Res.\u00a03, 1\u201348 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR43","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/11564089_7","volume-title":"Proceedings Algorithmic Learning Theory","author":"A. Gretton","year":"2005","unstructured":"Gretton, A., Bousquet, O., Smola, A., Sch\u00f6lkopf, B.: Measuring statistical dependence with Hilbert-Schmidt norms. In: Jain, S., Simon, H.U., Tomita, E. (eds.) Proceedings Algorithmic Learning Theory, pp. 63\u201377. Springer, Heidelberg (2005)"},{"key":"5_CR44","first-page":"2075","volume":"6","author":"A. Gretton","year":"2005","unstructured":"Gretton, A., Herbrich, R., Smola, A., Bousquet, O., Sch\u00f6lkopf, B.: Kernel methods for measuring independence. J. Mach. Learn. Res.\u00a06, 2075\u20132129 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR45","unstructured":"Shen, H., Jegelka, S., Gretton, A.: Fast kernel ICA using an approximate newton method. In: AISTATS 11 (2007)"},{"issue":"3","key":"5_CR46","doi-asserted-by":"publisher","first-page":"419","DOI":"10.2307\/1403753","volume":"61","author":"A. Feuerverger","year":"1993","unstructured":"Feuerverger, A.: A consistent test for bivariate dependence. International Statistical Review\u00a061(3), 419\u2013433 (1993)","journal-title":"International Statistical Review"},{"key":"5_CR47","unstructured":"Kankainen, A.: Consistent Testing of Total Independence Based on the Empirical Characteristic Function. PhD thesis, University of Jyv\u00e4skyl\u00e4 (1995)"},{"key":"5_CR48","unstructured":"Burges, C.J.C., Vapnik, V.: A new method for constructing artificial neural networks. Interim technical report, ONR contract N00014-94-c-0186, AT&T Bell Laboratories (1995)"},{"key":"5_CR49","volume-title":"Statistical Learning Theory","author":"V. Vapnik","year":"1998","unstructured":"Vapnik, V.: Statistical Learning Theory. John Wiley and Sons, New York (1998)"},{"key":"5_CR50","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.1016\/j.neucom.2005.12.029","volume":"69","author":"J. Anemuller","year":"2006","unstructured":"Anemuller, J., Duann, J.R., Sejnowski, T.J., Makeig, S.: Spatio-temporal dynamics in fmri recordings revealed with complex independent component analysis. Neurocomputing\u00a069, 1502\u20131512 (2006)","journal-title":"Neurocomputing"},{"key":"5_CR51","volume-title":"Support Vector Learning","author":"B. Sch\u00f6lkopf","year":"1997","unstructured":"Sch\u00f6lkopf, B.: Support Vector Learning. R.\u00a0Oldenbourg Verlag, Munich (1997), http:\/\/www.kernel-machines.org"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Song, L., Smola, A., Gretton, A., Borgwardt, K., Bedo, J.: Supervised feature selection via dependence estimation. In: Proc. Intl. Conf. Machine Learning (2007)","DOI":"10.1145\/1273496.1273600"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Song, L., Bedo, J., Borgwardt, K., Gretton, A., Smola, A.: Gene selection via the BAHSIC family of algorithms. In: Bioinformatics (ISMB) (to appear, 2007)","DOI":"10.1093\/bioinformatics\/btm216"},{"key":"5_CR54","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1038\/415530a","volume":"415","author":"L.J. van\u2019t Veer","year":"2002","unstructured":"van\u2019t Veer, L.J., Dai, H., van de Vijver, M.J., He, Y.D., Hart, A.A.M., et al.: Gene expression profiling predicts clinical outcome of breast cancer. Nature\u00a0415, 530\u2013536 (2002)","journal-title":"Nature"},{"issue":"15","key":"5_CR55","doi-asserted-by":"publisher","first-page":"5923","DOI":"10.1073\/pnas.0601231103","volume":"103","author":"L. Ein-Dor","year":"2006","unstructured":"Ein-Dor, L., Zuk, O., Domany, E.: Thousands of samples are needed to generate a robust gene list for predicting outcome in cancer. Proc. Natl. Acad. Sci. USA\u00a0103(15), 5923\u20135928 (2006)","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Bedo, J., Sanderson, C., Kowalczyk, A.: An efficient alternative to svm based recursive feature elimination with applications in natural language processing and bioinformatics. Artificial Intelligence (2006)","DOI":"10.1007\/11941439_21"},{"key":"5_CR57","doi-asserted-by":"crossref","unstructured":"Smyth, G.: Linear models and empirical bayes methods for assessing differential expressionin microarray experiments. Statistical Applications in Genetics and Molecular Biology\u00a03 (2004)","DOI":"10.2202\/1544-6115.1027"},{"key":"5_CR58","first-page":"31","volume":"12","author":"I. L\u00f6nnstedt","year":"2002","unstructured":"L\u00f6nnstedt, I., Speed, T.: Replicated microarray data. Statistica Sinica\u00a012, 31\u201346 (2002)","journal-title":"Statistica Sinica"},{"key":"5_CR59","unstructured":"Dud\u00edk, M., Schapire, R., Phillips, S.: Correcting sample selection bias in maximum entropy density estimation. Advances in Neural Information Processing Systems\u00a017 (2005)"},{"key":"5_CR60","volume-title":"Proc. Annual Conf. Computational Learning Theory","author":"M. Dud\u00edk","year":"2006","unstructured":"Dud\u00edk, M., Schapire, R.E.: Maximum entropy distribution estimation with generalized regularization. In: Lugosi, G., Simon, H.U. (eds.) Proc. Annual Conf. Computational Learning Theory, Springer, Heidelberg (2006)"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Hlawka, E.: Funktionen von beschr\u00e4nkter variation in der theorie der gleichverteilung. Annali di Mathematica Pura ed Applicata\u00a054 (1961)","DOI":"10.1007\/BF02415361"},{"key":"5_CR62","unstructured":"G\u00e4rtner, T., Flach, P.A., Kowalczyk, A., Smola, A.J.: Multi-instance kernels. IN: Proc. Intl. Conf. Machine Learning (2002)"},{"key":"5_CR63","series-title":"Lecture Notes in Artificial Intelligence","first-page":"57","volume-title":"Proceedings of the Sixteenth Annual Conference on Computational Learning Theory","author":"T. Jebara","year":"2003","unstructured":"Jebara, T., Kondor, I.: Bhattacharyya and expected likelihood kernels. In: Sch\u00f6lkopf, B., Warmuth, M.K. (eds.) COLT\/Kernel 2003. LNCS (LNAI), vol.\u00a02777, pp. 57\u201371. Springer, Heidelberg (2003)"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-75225-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T14:43:28Z","timestamp":1737470608000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-75225-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540752240","9783540752257"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-75225-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007]]}}}