{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:30:33Z","timestamp":1760596233318},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,4,13]],"date-time":"2012-04-13T00:00:00Z","timestamp":1334275200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1007\/s10994-012-5287-6","type":"journal-article","created":{"date-parts":[[2012,4,12]],"date-time":"2012-04-12T16:25:56Z","timestamp":1334247956000},"page":"381-407","source":"Crossref","is-referenced-by-count":10,"title":["Efficient cross-validation for kernelized least-squares regression with sparse basis expansions"],"prefix":"10.1007","volume":"87","author":[{"given":"Tapio","family":"Pahikkala","sequence":"first","affiliation":[]},{"given":"Hanna","family":"Suominen","sequence":"additional","affiliation":[]},{"given":"Jorma","family":"Boberg","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,4,13]]},"reference":[{"issue":"1","key":"5287_CR1","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s11063-010-9159-4","volume":"33","author":"A. Airola","year":"2011","unstructured":"Airola, A., Pahikkala, T., & Salakoski, T. (2011). On learning and cross-validation with decomposed Nystr\u00f6m approximation of kernel matrix. Neural Processing Letters, 33(1), 17\u201330.","journal-title":"Neural Processing Letters"},{"issue":"8","key":"5287_CR2","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1016\/j.patcog.2006.12.015","volume":"40","author":"S. An","year":"2007","unstructured":"An, S., Liu, W., & Venkatesh, S. (2007). Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression. Pattern Recognition, 40(8), 2154\u20132162.","journal-title":"Pattern Recognition"},{"key":"5287_CR3","first-page":"409","volume-title":"Advances in neural information processing systems","author":"G. Cauwenberghs","year":"2001","unstructured":"Cauwenberghs, G., & Poggio, T. (2001). Incremental and decremental support vector machine learning. In T. K. Leen, T. G. Dietterich, & V. Tresp (Eds.), Advances in neural information processing systems (Vol.\u00a013, pp. 409\u2013415). Cambridge: MIT Press."},{"issue":"10","key":"5287_CR4","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1016\/j.neunet.2004.07.002","volume":"17","author":"G. C. Cawley","year":"2004","unstructured":"Cawley, G. C., & Talbot, N. L. C. (2004). Fast exact leave-one-out cross-validation of sparse least-squares support vector machines. Neural Networks, 17(10), 1467\u20131475.","journal-title":"Neural Networks"},{"issue":"6","key":"5287_CR5","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1016\/j.csda.2010.01.024","volume":"54","author":"K. Brabanter De","year":"2010","unstructured":"De Brabanter, K., De Brabanter, J., Suykens, J., & De Moor, B. (2010). Optimized fixed-size kernel models for large data sets. Computational Statistics & Data Analysis, 54(6), 1484\u20131504.","journal-title":"Computational Statistics & Data Analysis"},{"issue":"7","key":"5287_CR6","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","volume":"10","author":"T. G. Dietterich","year":"1998","unstructured":"Dietterich, T. G. (1998). Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10(7), 1895\u20131923.","journal-title":"Neural Computation"},{"key":"5287_CR7","first-page":"55","volume":"6","author":"A. Elisseeff","year":"2005","unstructured":"Elisseeff, A., Evgeniou, T., & Pontil, M. (2005). Stability of randomized learning algorithms. Journal of Machine Learning Research, 6, 55\u201379.","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"5287_CR8","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1080\/00401706.1993.10485033","volume":"35","author":"I. E. Frank","year":"1993","unstructured":"Frank, I. E., & Friedman, J. H. (1993). A statistical view of some chemometrics regression tools. Technometrics, 35(2), 109\u2013135.","journal-title":"Technometrics"},{"key":"5287_CR9","volume-title":"Matrix computations","author":"G. H. Golub","year":"1989","unstructured":"Golub, G. H., & Van Loan, C. (1989). Matrix computations (2nd ed.). Baltimore: Johns Hopkins University Press.","edition":"2"},{"key":"5287_CR10","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-4473-3","volume-title":"Nonparametric regression and generalized linear models, a roughness penalty approach","author":"P. Green","year":"1994","unstructured":"Green, P., & Silverman, B. (1994). Nonparametric regression and generalized linear models, a roughness penalty approach. London: Chapman & Hall."},{"key":"5287_CR11","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511810817","volume-title":"Matrix analysis","author":"R. Horn","year":"1985","unstructured":"Horn, R., & Johnson, C. (1985). Matrix analysis. Cambridge: Cambridge University Press."},{"key":"5287_CR12","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/s00354-008-0067-3","volume":"27","author":"M. Karasuyama","year":"2009","unstructured":"Karasuyama, M., Takeuchi, I., & Nakano, R. (2009). Efficient leave-m-out cross-validation of support vector regression by generalizing decremental algorithm. New Generation Computing, 27, 307\u2013318.","journal-title":"New Generation Computing"},{"key":"5287_CR13","first-page":"1137","volume-title":"Proceedings of the fourteenth international joint conference on artificial intelligence","author":"R. Kohavi","year":"1995","unstructured":"Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In C. Mellish (Ed.), Proceedings of the fourteenth international joint conference on artificial intelligence (Vol.\u00a02, pp.\u00a01137\u20131143). San Mateo: Morgan Kaufmann."},{"key":"5287_CR14","series-title":"JMLR workshop and conference proceedings","first-page":"304","volume-title":"Proceedings of the 12th international conference on artificial intelligence and statistics","author":"S. Kumar","year":"2009","unstructured":"Kumar, S., Mohri, M., & Talwalkar, A. (2009). Sampling techniques for the Nystr\u00f6m method. In D. van Dyk & M. Welling (Eds.), JMLR workshop and conference proceedings: Vol. 5. Proceedings of the 12th international conference on artificial intelligence and statistics (pp. 304\u2013311)."},{"issue":"3","key":"5287_CR15","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1023\/A:1024068626366","volume":"52","author":"C. Nadeau","year":"2003","unstructured":"Nadeau, C., & Bengio, Y. (2003). Inference for the generalization error. Machine Learning, 52(3), 239\u2013281.","journal-title":"Machine Learning"},{"key":"5287_CR16","first-page":"83","volume-title":"Proceedings of the ninth Scandinavian conference on artificial intelligence (SCAI 2006)","author":"T. Pahikkala","year":"2006","unstructured":"Pahikkala, T., Boberg, J., & Salakoski, T. (2006a). Fast n-fold cross-validation for regularized least-squares. In T. Honkela, T. Raiko, J. Kortela, & H. Valpola (Eds.), Proceedings of the ninth Scandinavian conference on artificial intelligence (SCAI 2006) (pp. 83\u201390). Espoo: Helsinki University of Technology."},{"key":"5287_CR17","first-page":"181","volume-title":"Proceedings of the ECML\/PKDD\u201906 workshop on mining and learning with graphs","author":"T. Pahikkala","year":"2006","unstructured":"Pahikkala, T., Tsivtsivadze, E., Boberg, J., & Salakoski, T. (2006b). Graph kernels versus graph representations: a case study in parse ranking. In T. G\u00e4rtner, G. C. Garriga, & T. Meinl (Eds.), Proceedings of the ECML\/PKDD\u201906 workshop on mining and learning with graphs (pp. 181\u2013188)."},{"issue":"2","key":"5287_CR18","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10994-008-5082-6","volume":"74","author":"T. Pahikkala","year":"2009","unstructured":"Pahikkala, T., Pyysalo, S., Boberg, J., J\u00e4rvinen, J., & Salakoski, T. (2009a). Matrix representations, linear transformations, and kernels for disambiguation in natural language. Machine Learning, 74(2), 133\u2013158.","journal-title":"Machine Learning"},{"key":"5287_CR19","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/978-3-642-04921-7_36","volume-title":"Proceedings of the 9th international conference on adaptive and natural computing algorithms","author":"T. Pahikkala","year":"2009","unstructured":"Pahikkala, T., Suominen, H., Boberg, J., & Salakoski, T. (2009b). Efficient hold-out for subset of regressors. In M. Kolehmainen, P. Toivanen, & B. Beliczynski (Eds.), Proceedings of the 9th international conference on adaptive and natural computing algorithms (pp. 350\u2013359). Berlin: Springer."},{"issue":"1","key":"5287_CR20","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s10994-008-5097-z","volume":"75","author":"T. Pahikkala","year":"2009","unstructured":"Pahikkala, T., Tsivtsivadze, E., Airola, A., J\u00e4rvinen, J., & Boberg, J. (2009c). An efficient algorithm for learning to rank from preference graphs. Machine Learning, 75(1), 129\u2013165.","journal-title":"Machine Learning"},{"issue":"1\u20133","key":"5287_CR21","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.neucom.2005.02.015","volume":"69","author":"K. Pelckmans","year":"2005","unstructured":"Pelckmans, K., De Brabanter, J., Suykens, J., & De Moor, B. (2005). The differogram: non-parametric noise variance estimation and its use for model selection. Neurocomputing, 69(1\u20133), 100\u2013122.","journal-title":"Neurocomputing"},{"key":"5287_CR22","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s10994-005-5315-x","volume":"62","author":"K. Pelckmans","year":"2006","unstructured":"Pelckmans, K., Suykens, J., & De Moor, B. (2006). Additive regularization trade-off: fusion of training and validation levels in kernel methods. Machine Learning, 62, 217\u2013252.","journal-title":"Machine Learning"},{"issue":"9","key":"5287_CR23","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1109\/5.58326","volume":"78","author":"T. Poggio","year":"1990","unstructured":"Poggio, T., & Girosi, F. (1990). Networks for approximation and learning. Proceedings of the IEEE, 78(9), 1481\u20131497.","journal-title":"Proceedings of the IEEE"},{"issue":"5","key":"5287_CR24","first-page":"537","volume":"50","author":"T. Poggio","year":"2003","unstructured":"Poggio, T., & Smale, S. (2003). The mathematics of learning: Dealing with data. Notices of the American Mathematical Society, 50(5), 537\u2013544.","journal-title":"Notices of the American Mathematical Society"},{"key":"5287_CR25","first-page":"1939","volume":"6","author":"J. Qui\u00f1onero-Candela","year":"2005","unstructured":"Qui\u00f1onero-Candela, J., & Rasmussen, C. E. (2005). A unifying view of sparse approximate Gaussian process regression. Journal of Machine Learning Research, 6, 1939\u20131959.","journal-title":"Journal of Machine Learning Research"},{"key":"5287_CR26","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian processes for machine learning (adaptive computation and machine learning)","author":"C. E. Rasmussen","year":"2005","unstructured":"Rasmussen, C. E., & Williams, C. K. I. (2005). Gaussian processes for machine learning (adaptive computation and machine learning). Cambridge: MIT Press."},{"key":"5287_CR27","first-page":"101","volume":"5","author":"R. Rifkin","year":"2004","unstructured":"Rifkin, R., & Klautau, A. (2004). In defense of one-vs-all classification. Journal of Machine Learning Research, 5, 101\u2013141.","journal-title":"Journal of Machine Learning Research"},{"key":"5287_CR28","unstructured":"Rifkin, R., & Lippert, R. (2007). Notes on regularized least squares (Technical Report MIT-CSAIL-TR-2007-025). Massachusetts Institute of Technology, Cambridge, Massachusetts, USA."},{"key":"5287_CR29","series-title":"NATO science series III: Computer and system sciences, Chap. 7","first-page":"131","volume-title":"Advances in learning theory: methods, model and applications","author":"R. Rifkin","year":"2003","unstructured":"Rifkin, R., Yeo, G., & Poggio, T. (2003). Regularized least-squares classification. In J. Suykens, G. Horvath, S. Basu, C. Micchelli, & J. Vandewalle (Eds.), NATO science series III: Computer and system sciences, Chap. 7: Vol. 190. Advances in learning theory: methods, model and applications (pp. 131\u2013154). Amsterdam: IOS Press."},{"key":"5287_CR30","first-page":"515","volume-title":"Proceedings of the fifteenth international conference on machine learning","author":"C. Saunders","year":"1998","unstructured":"Saunders, C., Gammerman, A., & Vovk, V. (1998). Ridge regression learning algorithm in dual variables. In J. W. Shavlik (Ed.), Proceedings of the fifteenth international conference on machine learning (pp.\u00a0515\u2013521). San Mateo: Morgan Kaufmann."},{"issue":"3","key":"5287_CR31","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1111\/j.1751-5823.2000.tb00332.x","volume":"68","author":"R. A. Schiavo","year":"2000","unstructured":"Schiavo, R. A., & Hand, D. J. (2000). Ten more years of error rate research. International Statistical Review, 68(3), 295\u2013310.","journal-title":"International Statistical Review"},{"key":"5287_CR32","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1007\/3-540-44581-1_27","volume-title":"Proceedings of the 14th annual conference on computational learning theory","author":"B. Sch\u00f6lkopf","year":"2001","unstructured":"Sch\u00f6lkopf, B., Herbrich, R., & Smola, A. (2001). A generalized representer theorem. In D. Helmbold & R. Williamson (Eds.), Proceedings of the 14th annual conference on computational learning theory (pp.\u00a0416\u2013426). Berlin: Springer."},{"key":"5287_CR33","unstructured":"Shewchuk, J. R. (1994). An introduction to the conjugate gradient method without the agonizing pain (Technical report). Carnegie Mellon University, Pittsburgh, PA, USA."},{"key":"5287_CR34","first-page":"619","volume-title":"Advances in neural information processing systems","author":"A. Smola","year":"2001","unstructured":"Smola, A., & Bartlett, P. (2001). Sparse greedy gaussian process regression. In T. K. Leen, T. G. Dietterich, & V. Tresp (Eds.), Advances in neural information processing systems (Vol.\u00a03, pp. 619\u2013625). Cambridge: MIT Press."},{"issue":"3","key":"5287_CR35","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","volume":"9","author":"J. Suykens","year":"1999","unstructured":"Suykens, J., & Vandewalle, J. (1999a). Least squares support vector machine classifiers. Neural Processing Letters, 9(3), 293\u2013300.","journal-title":"Neural Processing Letters"},{"key":"5287_CR36","first-page":"900","volume-title":"International joint conference on neural networks (IJCNN\u201999)","author":"J. Suykens","year":"1999","unstructured":"Suykens, J., & Vandewalle, J. (1999b). Multiclass least squares support vector machines. In International joint conference on neural networks (IJCNN\u201999) (Vol.\u00a02, pp. 900\u2013903). New York: Inst. Elect. Electronics Eng."},{"key":"5287_CR37","doi-asserted-by":"crossref","DOI":"10.1142\/9789812776655","volume-title":"Least squares support vector machines","author":"J. Suykens","year":"2002","unstructured":"Suykens, J., Van Gestel, T., De Brabanter, J., De Moor, B., & Vandewalle, J. (2002). Least squares support vector machines. Singapore: World Scientific."},{"key":"5287_CR38","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The nature of statistical learning theory","author":"V. Vapnik","year":"1995","unstructured":"Vapnik, V. (1995). The nature of statistical learning theory. New York: Springer."},{"key":"5287_CR39","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1023\/A:1013955821559","volume":"48","author":"P. Vincent","year":"2002","unstructured":"Vincent, P., & Bengio, Y. (2002). Kernel matching pursuit. Machine Learning, 48, 165\u2013187.","journal-title":"Machine Learning"},{"key":"5287_CR40","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970128","volume-title":"Spline models for observational data. series in applied mathematics","author":"G. Wahba","year":"1990","unstructured":"Wahba, G. (1990). Spline models for observational data. series in applied mathematics (Vol.\u00a059). Philadelphia: SIAM."},{"key":"5287_CR41","first-page":"682","volume-title":"Advances in neural information processing systems","author":"C. K. I. Williams","year":"2001","unstructured":"Williams, C. K. I., & Seeger, M. (2001). Using the Nystr\u00f6m method to speed up kernel machines. In T. K. Leen, T. G. Dietterich, & V. Tresp (Eds.), Advances in neural information processing systems (Vol.\u00a013, pp. 682\u2013688). Cambridge: MIT Press."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-012-5287-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-012-5287-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-012-5287-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,27]],"date-time":"2019-06-27T02:11:32Z","timestamp":1561601492000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-012-5287-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,4,13]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["5287"],"URL":"https:\/\/doi.org\/10.1007\/s10994-012-5287-6","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,4,13]]}}}