{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T13:20:15Z","timestamp":1762867215635,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,9,19]],"date-time":"2017-09-19T00:00:00Z","timestamp":1505779200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s10994-017-5664-2","type":"journal-article","created":{"date-parts":[[2017,9,19]],"date-time":"2017-09-19T20:51:42Z","timestamp":1505854302000},"page":"509-549","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["The randomized information coefficient: assessing dependencies in noisy data"],"prefix":"10.1007","volume":"107","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-0662","authenticated-orcid":false,"given":"Simone","family":"Romano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nguyen Xuan","family":"Vinh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8661-1544","authenticated-orcid":false,"given":"Karin","family":"Verspoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Bailey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,19]]},"reference":[{"key":"5664_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45, 5\u201332.","journal-title":"Machine Learning"},{"issue":"391","key":"5664_CR2","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1080\/01621459.1985.10478157","volume":"80","author":"L Breiman","year":"1985","unstructured":"Breiman, L., & Friedman, J. H. (1985). Estimating optimal transformations for multiple regression and correlation. Journal of the American statistical Association, 80(391), 580\u2013598.","journal-title":"Journal of the American statistical Association"},{"issue":"6","key":"5664_CR3","doi-asserted-by":"publisher","first-page":"066208","DOI":"10.1103\/PhysRevE.71.066208","volume":"71","author":"C Cellucci","year":"2005","unstructured":"Cellucci, C., Albano, A. M., & Rapp, P. (2005). Statistical validation of mutual information calculations: Comparison of alternative numerical algorithms. Physical Review E, 71(6), 066208.","journal-title":"Physical Review E"},{"key":"5664_CR4","volume-title":"Elements of information theory","author":"TM Cover","year":"2012","unstructured":"Cover, T. M., & Thomas, J. A. (2012). Elements of information theory. New York: Wiley."},{"key":"5664_CR5","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J. (2006). Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research, 7, 1\u201330.","journal-title":"The Journal of Machine Learning Research"},{"key":"5664_CR6","first-page":"194","volume":"12","author":"J Dougherty","year":"1995","unstructured":"Dougherty, J., Kohavi, R., Sahami, M., et al. (1995). Supervised and unsupervised discretization of continuous features. Machine learning: Proceedings of the twelfth international conference, 12, 194\u2013202.","journal-title":"Machine learning: Proceedings of the twelfth international conference"},{"key":"5664_CR7","unstructured":"Faivishevsky, L. & Goldberger, J. (2009). ICA based on a smooth estimation of the differential entropy. In Advances in neural information processing systems (pp. 433\u2013440)."},{"key":"5664_CR8","unstructured":"Fayyad, U. & Irani, K. (1993). Multi-interval discretization of continuous-valued attributes for classification learning. In International joint conference on artificial intelligence (IJCAI)"},{"issue":"2","key":"5664_CR9","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1103\/PhysRevA.33.1134","volume":"33","author":"AM Fraser","year":"1986","unstructured":"Fraser, A. M., & Swinney, H. L. (1986). Independent coordinates for strange attractors from mutual information. Physical Review A, 33(2), 1134.","journal-title":"Physical Review A"},{"issue":"4","key":"5664_CR10","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1109\/TKDE.2012.35","volume":"25","author":"S Garcia","year":"2013","unstructured":"Garcia, S., Luengo, J., S\u00e1ez, J. A., L\u00f3pez, V., & Herrera, F. (2013). A survey of discretization techniques: Taxonomy and empirical analysis in supervised learning. IEEE Transactions on Knowledge and Data Engineering, 25(4), 734\u2013750.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"5664_CR11","unstructured":"Geurts, P. (2002). Bias\/variance tradeoff and time series classification. PhD thesis, Department d\u2019\u00c9letrecit\u00e9, \u00c9letronique et Informatique. Institut Momntefiore. Unversit\u00e9 de Li\u00e8ge."},{"issue":"1","key":"5664_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3\u201342.","journal-title":"Machine Learning"},{"issue":"1","key":"5664_CR13","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K. M., Rasch, M. J., Sch\u00f6lkopf, B., & Smola, A. (2012). A kernel two-sample test. The Journal of Machine Learning Research, 13(1), 723\u2013773.","journal-title":"The Journal of Machine Learning Research"},{"key":"5664_CR14","doi-asserted-by":"crossref","unstructured":"Gretton, A., Bousquet, O., Smola, A., & Sch\u00f6lkopf, B. (2005). Measuring statistical dependence with Hilbert\u2013Schmidt norms. In Algorithmic learning theory (pp. 63\u201377). Springer.","DOI":"10.1007\/11564089_7"},{"issue":"2","key":"5664_CR15","doi-asserted-by":"publisher","first-page":"e87446","DOI":"10.1371\/journal.pone.0087446","volume":"9","author":"X Guo","year":"2014","unstructured":"Guo, X., Zhang, Y., Hu, W., Tan, H., & Wang, X. (2014). Inferring nonlinear gene regulatory networks from gene expression data based on distance correlation. PloS ONE, 9(2), e87446.","journal-title":"PloS ONE"},{"key":"5664_CR16","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, 1157\u20131182.","journal-title":"The Journal of Machine Learning Research"},{"key":"5664_CR17","unstructured":"Huo, X. & Szekely, G.\u00a0J. (2014). Fast computing for distance covariance. ArXiv preprint arXiv:1410.1503 ."},{"key":"5664_CR18","doi-asserted-by":"crossref","unstructured":"Khan, S., Bandyopadhyay, S., Ganguly, A. R., Saigal, S., Erickson, D. J., I. I. I., Protopopescu, V., et al. (2007). Relative performance of mutual information estimation methods for quantifying the dependence among short and noisy data. Physical Review E, 76(2), 026209.","DOI":"10.1103\/PhysRevE.76.026209"},{"issue":"6","key":"5664_CR19","first-page":"066138","volume":"69","author":"A Kraskov","year":"2004","unstructured":"Kraskov, A., St\u00f6gbauer, H., & Grassberger, P. (2004). Estimating mutual information. Physical Review E, 69(6), 066138.","journal-title":"Estimating mutual information. Physical Review E"},{"issue":"10","key":"5664_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v061.i10","volume":"61","author":"MB Kursa","year":"2014","unstructured":"Kursa, M. B. (2014). rFerns: An implementation of the random ferns method for general-purpose machine learning. Journal of Statistical Software, 61(10), 1\u201313.","journal-title":"Journal of Statistical Software"},{"issue":"3","key":"5664_CR21","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1109\/TSMC.1987.4309069","volume":"17","author":"TO Kvalseth","year":"1987","unstructured":"Kvalseth, T. O. (1987). Entropy and correlation: Some comments. IEEE transactions on Systems, Man and Cybernetics, 17(3), 517\u2013519.","journal-title":"IEEE transactions on Systems, Man and Cybernetics"},{"key":"5664_CR22","unstructured":"Lippert, C., Stegle, O., Ghahramani, Z., & Borgwardt, K.\u00a0M. (2009). A kernel method for unsupervised structured network inference. In International conference on artificial intelligence and statistics (pp. 368\u2013375)."},{"key":"5664_CR23","unstructured":"Lizier, J.\u00a0T. (2014). JIDT: An information-theoretic toolkit for studying the dynamics of complex systems. ArXiv preprint arXiv:1408.3270 ."},{"key":"5664_CR24","unstructured":"Lopez-Paz, D., Hennig, P., & Sch\u00f6lkopf, B. (2013). The randomized dependence coefficient. In Advances in neural information processing systems (pp. 1\u20139)."},{"key":"5664_CR25","unstructured":"Luedtke, A. & Tran, L. (2013). The generalized mean information coefficient. ArXiv preprint arXiv:1308.5712 ."},{"issue":"Suppl 1","key":"5664_CR26","doi-asserted-by":"publisher","first-page":"S7","DOI":"10.1186\/1471-2105-7-S1-S7","volume":"7","author":"AA Margolin","year":"2006","unstructured":"Margolin, A. A., Nemenman, I., Basso, K., Wiggins, C., Stolovitzky, G., Favera, R. D., et al. (2006). Aracne: An algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context. BMC Bioinformatics, 7(Suppl 1), S7.","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"5664_CR27","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/0165-1684(89)90132-1","volume":"16","author":"R Moddemeijer","year":"1989","unstructured":"Moddemeijer, R. (1989). On estimation of entropy and mutual information of continuous distributions. Signal Processing, 16(3), 233\u2013248.","journal-title":"Signal Processing"},{"issue":"3","key":"5664_CR28","doi-asserted-by":"publisher","first-page":"2318","DOI":"10.1103\/PhysRevE.52.2318","volume":"52","author":"Y-I Moon","year":"1995","unstructured":"Moon, Y.-I., Rajagopalan, B., & Lall, U. (1995). Estimation of mutual information using kernel density estimators. Physical Review E, 52(3), 2318.","journal-title":"Physical Review E"},{"key":"5664_CR29","unstructured":"Nguyen, H.\u00a0V., M\u00fcller, E., Vreeken, J., Efros, P., & B\u00f6hm, K. (2014a). Multivariate maximal correlation analysis. In Proceedings of the 31st international conference on machine learning (ICML-14) (pp. 775\u2013783)."},{"key":"5664_CR30","unstructured":"Nguyen, H.\u00a0V. & Vreeken, J. (2015). Universal dependency analysis. ArXiv preprint arXiv:1510.08389 ."},{"key":"5664_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, X.\u00a0V., Chan, J., Romano, S., & Bailey, J. (2014b). Effective global approaches for mutual information based feature selection. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 512\u2013521). ACM.","DOI":"10.1145\/2623330.2623611"},{"key":"5664_CR32","doi-asserted-by":"crossref","unstructured":"\u00d6zuysal, M., Fua, P., & Lepetit, V. (2007). Fast keypoint recognition in ten lines of code. In CVPR.","DOI":"10.1109\/CVPR.2007.383123"},{"issue":"6062","key":"5664_CR33","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1126\/science.1205438","volume":"334","author":"DN Reshef","year":"2011","unstructured":"Reshef, D. N., Reshef, Y. A., Finucane, H. K., Grossman, S. R., McVean, G., Turnbaugh, P. J., et al. (2011). Detecting novel associations in large data sets. Science, 334(6062), 1518\u20131524.","journal-title":"Science"},{"key":"5664_CR34","unstructured":"Reshef, D. N., Reshef, Y.\u00a0A., Sabeti, P.\u00a0C., & Mitzenmacher, M.\u00a0M. (2015a). An empirical study of leading measures of dependence. ArXiv preprint arXiv:1505.02214 ."},{"key":"5664_CR35","unstructured":"Reshef, Y. A., Reshef, D. N., Finucane, H. K., Sabeti, P. C., & Mitzenmacher, M, M. (2015b). Measuring dependence powerfully and equitably. ArXiv preprint arXiv:1505.02213 ."},{"key":"5664_CR36","unstructured":"Romano, S., Bailey, J., Nguyen, V., & Verspoor, K. (2014). Standardized mutual information for clustering comparisons: One step further in adjustment for chance. In Proceedings of the 31st international conference on machine learning (ICML-14) (pp. 1143\u20131151)."},{"key":"5664_CR37","doi-asserted-by":"crossref","unstructured":"Romano, S., Vinh, N.\u00a0X., Bailey, J., & Verspoor, K. (2016). A framework to adjust dependency measure estimates for chance. In Proceedings of the 2016 SIAM international conference on data mining (pp. 423\u2013431). Society for Industrial and Applied Mathematics.","DOI":"10.1137\/1.9781611974348.48"},{"key":"5664_CR38","volume-title":"A first course in probability","author":"S Ross","year":"2012","unstructured":"Ross, S. (2012). A first course in probability. Upper Saddle River: Pearson."},{"key":"5664_CR39","doi-asserted-by":"crossref","unstructured":"Schaffernicht, E., Kaltenhaeuser, R., Verma, S.\u00a0S., & Gross, H.-M. (2010). On estimating mutual information for feature selection. In Artificial neural networks ICANN 2010 (pp. 362\u2013367). Springer.","DOI":"10.1007\/978-3-642-15819-3_48"},{"key":"5664_CR40","unstructured":"Simon, N. & Tibshirani, R. (2011). Comment on detecting novel associations in large data sets. ArXiv preprint arXiv:1401.7645 ."},{"key":"5664_CR41","doi-asserted-by":"crossref","unstructured":"Song, L., Smola, A., Gretton, A., Borgwardt, K.\u00a0M., & Bedo, J. (2007). Supervised feature selection via dependence estimation. In Proceedings of the 24th international conference on Machine learning (pp. 823\u2013830). ACM.","DOI":"10.1145\/1273496.1273600"},{"issue":"suppl 2","key":"5664_CR42","doi-asserted-by":"publisher","first-page":"S231","DOI":"10.1093\/bioinformatics\/18.suppl_2.S231","volume":"18","author":"R Steuer","year":"2002","unstructured":"Steuer, R., Kurths, J., Daub, C. O., Weise, J., & Selbig, J. (2002). The mutual information: Detecting and evaluating dependencies between variables. Bioinformatics, 18(suppl 2), S231\u2013S240.","journal-title":"Bioinformatics"},{"key":"5664_CR43","unstructured":"Sugiyama, M. & Borgwardt, K.\u00a0M. (2013). Measuring statistical dependence via the mutual information dimension. In Proceedings of the twenty-third international joint conference on artificial intelligence (pp. 1692\u20131698). AAAI Press."},{"issue":"4","key":"5664_CR44","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1214\/09-AOAS312","volume":"3","author":"GJ Sz\u00e9kely","year":"2009","unstructured":"Sz\u00e9kely, G. J., Rizzo, M. L., et al. (2009). Brownian distance covariance. The Annals of Applied Statistics, 3(4), 1236\u20131265.","journal-title":"The Annals of Applied Statistics"},{"key":"5664_CR45","first-page":"11","volume":"10","author":"D Tang","year":"2014","unstructured":"Tang, D., Wang, M., Zheng, W., & Wang, H. (2014). Rapidmic: Rapid computation of the maximal information coefficient. Evolutionary Bioinformatics Online, 10, 11.","journal-title":"Evolutionary Bioinformatics Online"},{"issue":"1","key":"5664_CR46","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/1471-2105-7-43","volume":"7","author":"T Bulcke Van den","year":"2006","unstructured":"Van den Bulcke, T., Van Leemput, K., Naudts, B., van Remortel, P., Ma, H., Verschoren, A., et al. (2006). Syntren: A generator of synthetic gene expression data for design and analysis of structure learning algorithms. BMC Bioinformatics, 7(1), 43.","journal-title":"BMC Bioinformatics"},{"issue":"2","key":"5664_CR47","doi-asserted-by":"publisher","first-page":"306","DOI":"10.3390\/cells2020306","volume":"2","author":"AF Villaverde","year":"2013","unstructured":"Villaverde, A. F., Ross, J., & Banga, J. R. (2013). Reverse engineering cellular networks with information theoretic methods. Cells, 2(2), 306\u2013329.","journal-title":"Cells"},{"issue":"5","key":"5664_CR48","doi-asserted-by":"publisher","first-page":"e96732","DOI":"10.1371\/journal.pone.0096732","volume":"9","author":"AF Villaverde","year":"2014","unstructured":"Villaverde, A. F., Ross, J., Mor\u00e1n, F., & Banga, J. R. (2014). MIDER: Network inference with mutual information distance and entropy reduction. PloS ONE, 9(5), e96732.","journal-title":"PloS ONE"},{"key":"5664_CR49","first-page":"2837","volume":"11","author":"NX Vinh","year":"2010","unstructured":"Vinh, N. X., Epps, J., & Bailey, J. (2010). Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance. Journal of Machine Learning Research, 11, 2837\u20132854.","journal-title":"Journal of Machine Learning Research"},{"issue":"12","key":"5664_CR50","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1109\/TPAMI.2012.48","volume":"34","author":"J Wang","year":"2012","unstructured":"Wang, J., Kumar, S., & Chang, S.-F. (2012). Semi-supervised hashing for large-scale search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(12), 2393\u20132406.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5664_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., Romano, S., Nguyen, V., Bailey, J., Ma, X., & Xia, S.-T. (2017). Unbiased multivariate correlation analysis.","DOI":"10.1609\/aaai.v31i1.10778"},{"issue":"1","key":"5664_CR52","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/1471-2105-13-131","volume":"13","author":"N Xuan","year":"2012","unstructured":"Xuan, N., Chetty, M., Coppel, R., & Wangikar, P. (2012). Gene regulatory network modeling via global optimization of high-order dynamic bayesian network. BMC Bioinformatics, 13(1), 131.","journal-title":"BMC Bioinformatics"},{"key":"5664_CR53","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1038\/srep06662","volume":"4","author":"Y Zhang","year":"2014","unstructured":"Zhang, Y., Jia, S., Huang, H., Qiu, J., & Zhou, C. (2014). A novel algorithm for the precise calculation of the maximal information coefficient. Scientific Reports, 4, 6662.","journal-title":"Scientific Reports"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-017-5664-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-017-5664-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-017-5664-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T01:35:36Z","timestamp":1659490536000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-017-5664-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,19]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["5664"],"URL":"https:\/\/doi.org\/10.1007\/s10994-017-5664-2","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2017,9,19]]}}}