{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:43:02Z","timestamp":1754109782941},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10994-022-06166-z","type":"journal-article","created":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T18:02:42Z","timestamp":1651514562000},"page":"2631-2662","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Variance reduction in feature hashing using MLE and control variate method"],"prefix":"10.1007","volume":"111","author":[{"given":"Bhisham Dev","family":"Verma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rameshwar","family":"Pratap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manoj","family":"Thakur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,2]]},"reference":[{"issue":"4","key":"6166_CR1","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1016\/S0022-0000(03)00025-4","volume":"66","author":"Dimitris Achlioptas","year":"2003","unstructured":"Achlioptas, Dimitris. (2003). Database-friendly random projections: Johnson-lindenstrauss with binary coins. The Journal of Computer and System Sciences, 66(4), 671\u2013687.","journal-title":"The Journal of Computer and System Sciences"},{"key":"6166_CR2","unstructured":"Agarwal, A, Chapelle, O., Dud\u00edk, M., & Langford, J. (2014). A reliable effective terascale linear learning system., 15, 1111\u20131133."},{"issue":"3731","key":"6166_CR3","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"Richard Bellman","year":"1966","unstructured":"Bellman, Richard. (1966). Dynamic programming. Science, 153(3731), 34\u201337.","journal-title":"Science"},{"key":"6166_CR4","doi-asserted-by":"crossref","unstructured":"Broder, A.Z., Charikar, M., Frieze, A.M., & Mitzenmacher, M. (1998). Min-wise independent permutations (extended abstract). In Proceedings of the Thirtieth Annual ACM Symposium on the Theory of Computing, Dallas, Texas, USA, May 23-26, 1998, pp. 327\u2013336.","DOI":"10.1145\/276698.276781"},{"key":"6166_CR5","volume-title":"Ars magna or the rules of algebra","author":"G Cardano","year":"1993","unstructured":"Cardano, G. (1993). Ars magna or the rules of algebra. Dover Publications."},{"key":"6166_CR6","doi-asserted-by":"crossref","unstructured":"Charikar, M. (2002). Similarity estimation techniques from rounding algorithms. In Proceedings on 34th Annual ACM Symposium on Theory of Computing, May 19-21, 2002, Montr\u00e9al, Qu\u00e9bec, Canada, pp. 380\u2013388.","DOI":"10.1145\/509907.509965"},{"key":"6166_CR7","unstructured":"Chen, W., Wilson, J., Tyree, S., Weinberger, K., & Chen, Y. (2015). Compressing neural networks with the hashing trick. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume\u00a037 of Proceedings of Machine Learning Research, pp. 2285\u20132294, Lille, France, 07\u201309 Jul 2015. PMLR."},{"key":"6166_CR8","doi-asserted-by":"crossref","unstructured":"Dasgupta, A., Kumar, R., & Sarl\u00f3s, T., (2010). A sparse johnson: Lindenstrauss transform. In Proceedings of the 42nd ACM Symposium on Theory of Computing, STOC 2010, Cambridge, Massachusetts, USA, 5-8 June 2010, pp. 341\u2013350.","DOI":"10.1145\/1806689.1806737"},{"issue":"1","key":"6166_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1002\/rsa.10073","volume":"22","author":"S Dasgupta","year":"2003","unstructured":"Dasgupta, S., & Gupta, A. (2003). An elementary proof of a theorem of johnson and lindenstrauss. Random Structures and Algorithms, 22(1), 60\u201365.","journal-title":"Random Structures and Algorithms"},{"key":"6166_CR10","doi-asserted-by":"crossref","unstructured":"Ertl, O. (2018). Bagminhash-minwise hashing algorithm for weighted sets. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1368\u20131377.","DOI":"10.1145\/3219819.3220089"},{"key":"6166_CR11","volume-title":"An Introduction to Probability Theory and Its Applications","author":"W Feller","year":"1968","unstructured":"Feller, W. (1968). An Introduction to Probability Theory and Its Applications (Vol. 1). Wiley."},{"key":"6166_CR12","first-page":"545","volume-title":"Advances in Neural Information Processing Systems 17","author":"I Guyon","year":"2005","unstructured":"Guyon, I., Gunn, S., Ben-Hur, A., & Dror, G. (2005). Result analysis of the nips 2003 feature selection challenge. In L. K. Saul, Y. Weiss, & L. Bottou (Eds.), Advances in Neural Information Processing Systems 17 (pp. 545\u2013552). MIT Press."},{"issue":"3","key":"6166_CR13","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1145\/1147954.1147955","volume":"53","author":"P Indyk","year":"2006","unstructured":"Indyk, P. (2006). Stable distributions, pseudorandom generators, embeddings, and data stream computation. Journal of the ACM (JACM), 53(3), 307\u2013323.","journal-title":"Journal of the ACM (JACM)"},{"key":"6166_CR14","doi-asserted-by":"crossref","unstructured":"Ioffe, S. (2010). Improved consistent sampling, weighted minhash and l1 sketching. In 2010 IEEE International Conference on Data Mining, pp. 246\u2013255. IEEE.","DOI":"10.1109\/ICDM.2010.80"},{"key":"6166_CR15","unstructured":"Ji, J., Li, J., Yan, S., Zhang, B., & Tian, Q. (2012). Super-bit locality-sensitive hashing. In Advances in neural information processing systems, pp. 108\u2013116."},{"key":"6166_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, W.B., & Lindenstrauss, J. (1983). Extensions of lipschitz mappings into a hilbert space. Conference in modern analysis and probability (New Haven, Conn., 1982), Amer. Math. Soc., Providence, R.I., pages 189\u2013206.","DOI":"10.1090\/conm\/026\/737400"},{"key":"6166_CR17","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Douze, M., J\u00e9gou, H., & Mikolov, T. (2016). Fasttext.zip: Compressing text classification models. CoRR, arXiv:abs\/1612.03651."},{"key":"6166_CR18","doi-asserted-by":"crossref","unstructured":"Kang, K. (2017). Using the multivariate normal to improve random projections. In Intelligent Data Engineering and Automated Learning - IDEAL 2017 - 18th International Conference, Guilin, China, October 30 - November 1, 2017, Proceedings, pp. 397\u2013405.","DOI":"10.1007\/978-3-319-68935-7_43"},{"key":"6166_CR19","doi-asserted-by":"crossref","unstructured":"Kang, K., & Hooker, G. (2017). Random projections with control variates. In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017, Porto, Portugal, February 24-26, 2017, pp. 138\u2013147.","DOI":"10.5220\/0006188801380147"},{"key":"6166_CR20","unstructured":"Kang, K., & Pin, W.W. (2018). Improving sign random projections with additional information. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018, pp. 2484\u20132492."},{"key":"6166_CR21","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1287\/mnsc.27.3.322","volume":"27","author":"S Lavenberg","year":"1981","unstructured":"Lavenberg, S., & Welch, P. (1981). A perspective on the use of control variables to increase the efficiency of monte carlo simulations. Management Science, 27, 322\u2013335.","journal-title":"Management Science"},{"key":"6166_CR22","unstructured":"Li, P. (2007). Very sparse stable random projections for dimension reduction in l $$\\alpha $$ ($$0< \\alpha \\le 2$$) norm. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 440\u2013449."},{"key":"6166_CR23","unstructured":"Li, P. (2008). Estimators and tail bounds for dimension reduction in $$l_\\alpha $$ ($$0< \\alpha \\le 2$$) using stable random projections. In Proceedings of the nineteenth annual ACM-SIAM symposium on Discrete algorithms, pp. 10\u201319."},{"key":"6166_CR24","doi-asserted-by":"crossref","unstructured":"Li, P. (2019). Sign-full random projections. In Proceedings of the AAAI Conference on Artificial Intelligence, 33, 4205\u20134212.","DOI":"10.1609\/aaai.v33i01.33014205"},{"key":"6166_CR25","unstructured":"Li, P., & Hastie, T. (2007). A unified near-optimal estimator for dimension reduction in $$l_\\alpha $$ ($$0< \\alpha \\le 2$$) using stable random projections. In NIPS, pp. 905\u2013912. Citeseer."},{"key":"6166_CR26","unstructured":"Li, P., Hastie, T., & Church, K.W. (2006). Practical Procedures for Dimension Reduction in l1. Citeseer."},{"key":"6166_CR27","doi-asserted-by":"crossref","unstructured":"Li, P., Hastie, T., & Church, K.W. (2006). Improving random projections using marginal information. In Learning Theory, 19th Annual Conference on Learning Theory, COLT 2006, Pittsburgh, PA, USA, June 22-25, 2006, Proceedings, pp. 635\u2013649.","DOI":"10.1007\/11776420_46"},{"key":"6166_CR28","doi-asserted-by":"crossref","unstructured":"Li, P., Hastie, T., & Church, K.W. (2006). Very sparse random projections. In Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, August 20-23, 2006, pp. 287\u2013296.","DOI":"10.1145\/1150402.1150436"},{"issue":"8","key":"6166_CR29","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1145\/1978542.1978566","volume":"54","author":"P Li","year":"2011","unstructured":"Li, P., & K\u00f6nig, A. C. (2011). Theory and applications of b-bit minwise hashing. Commun. ACM, 54(8), 101\u2013109.","journal-title":"Commun. ACM"},{"key":"6166_CR30","unstructured":"Li, P, Owen, A., & Zhang, C.H. (2012). One permutation hashing. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States, pp. 3122\u20133130."},{"key":"6166_CR31","unstructured":"Li, X, & Li, P. (2019). Random projections with asymmetric quantization. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp. 10858\u201310867."},{"key":"6166_CR32","doi-asserted-by":"publisher","first-page":"78590","DOI":"10.1109\/ACCESS.2020.2990422","volume":"8","author":"Yulong Li","year":"2020","unstructured":"Li, Yulong, Kuang, Zhihao, Li, Jiang Yan, & Kang, Keegan. (2020). Improving random projections with extra vectors to approximate inner products. IEEE Access, 8, 78590\u201378607.","journal-title":"IEEE Access"},{"key":"6166_CR33","unstructured":"Lichman, M. (2013). UCI machine learning repository."},{"key":"6166_CR34","doi-asserted-by":"crossref","unstructured":"Mensink, T., Verbeek, J., Perronnin, F., & Csurka, G., (2012). Metric learning for large scale image classification: Generalizing to new classes at near-zero cost. In Computer Vision - ECCV 2012 - 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II, pp. 488\u2013501.","DOI":"10.1007\/978-3-642-33709-3_35"},{"key":"6166_CR35","unstructured":"Murphy, K.P. (2013). Machine learning : a probabilistic perspective. MIT Press, Cambridge, Mass. [u.a.]."},{"key":"6166_CR36","doi-asserted-by":"crossref","unstructured":"Pratap, R., Bera, D., Revanuru, K., (2019). Efficient sketching algorithm for sparse binary data. In Jianyong Wang, Kyuseok Shim, and Xindong Wu, editors, 2019 IEEE International Conference on Data Mining, ICDM 2019, Beijing, China, November 8-11, 2019, pp. 508\u2013517. IEEE.","DOI":"10.1109\/ICDM.2019.00061"},{"key":"6166_CR37","doi-asserted-by":"crossref","unstructured":"Pratap, R., Kulkarni, R., & Sohony, I. (2018). Efficient dimensionality reduction for sparse binary data. In Naoki Abe, Huan Liu, Calton Pu, Xiaohua Hu, Nesreen\u00a0K. Ahmed, Mu\u00a0Qiao, Yang Song, Donald Kossmann, Bing Liu, Kisung Lee, Jiliang Tang, Jingrui He, and Jeffrey\u00a0S. Saltz, editors, IEEE International Conference on Big Data, Big Data 2018, Seattle, WA, USA, December 10-13, 2018, pages 152\u2013157. IEEE.","DOI":"10.1109\/BigData.2018.8622338"},{"key":"6166_CR38","unstructured":"Provost, S.B., & Mathai, A.M. (1992). Quadratic Forms in Random Variables: Theory and Applications\/ A.M. Mathai, Serge B. Provost. Statistics : textbooks and monographs. Marcel Dek ker."},{"key":"6166_CR39","unstructured":"Shrivastava, A. (2016). Simple and efficient weighted minwise hashing. In Advances in Neural Information Processing Systems, pages 1498\u20131506."},{"key":"6166_CR40","unstructured":"Shrivastava, A. (2017). Optimal densification for fast and accurate minwise hashing. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, pages 3154\u20133163."},{"key":"6166_CR41","unstructured":"Shrivastava, A., & Li, P. (2014). In defense of minhash over simhash. In Artificial Intelligence and Statistics, pages 886\u2013894. PMLR."},{"key":"6166_CR42","doi-asserted-by":"crossref","unstructured":"Weinberger, K., Dasgupta, A., Langford, J., Smola, A., & Attenberg, J. (2009). Feature hashing for large scale multitask learning. In Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, June 14\u201318, 2009, pages 1113\u20131120.","DOI":"10.1145\/1553374.1553516"},{"issue":"12","key":"6166_CR43","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1109\/TKDE.2018.2876250","volume":"31","author":"Wu Wei","year":"2018","unstructured":"Wei, Wu., Li, Bin, Chen, Ling, Zhang, Chengqi, & Philip, S\u00a0Yu. (2018). Improved consistent weighted sampling revisited. IEEE Transactions on Knowledge and Data Engineering, 31(12), 2332\u20132345.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"1","key":"6166_CR44","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TKDE.2013.109","volume":"26","author":"X Wu","year":"2014","unstructured":"Wu, X., Zhu, X., Wu, G., & Ding, W. (2014). Data mining with big data. IEEE Transactions on Knowledge and Data Engineering, 26(1), 97\u2013107.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6166_CR45","unstructured":"Yu, F., Kumar, S., Gong, Y., & Chang, S.F., (2014). Circulant binary embedding. In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32, ICML\u201914, pages II\u2013946\u2013II\u2013954. JMLR.org."},{"issue":"3","key":"6166_CR46","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MCI.2014.2326099","volume":"9","author":"Y Zhai","year":"2014","unstructured":"Zhai, Y., Ong, Y., & Tsang, I. W. (2014). The emerging \u201cbig dimensionality\u2019\u2019. IEEE Computational Intelligence Magazine, 9(3), 14\u201326.","journal-title":"IEEE Computational Intelligence Magazine"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-022-06166-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-022-06166-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-022-06166-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T00:03:17Z","timestamp":1682985797000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-022-06166-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":46,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["6166"],"URL":"https:\/\/doi.org\/10.1007\/s10994-022-06166-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,2]]},"assertion":[{"value":"24 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"All authors participated in this study give the publisher the permission to publish this work.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Please contact the authors for code.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}