{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:10:09Z","timestamp":1739319009276,"version":"3.37.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2009,9,3]],"date-time":"2009-09-03T00:00:00Z","timestamp":1251936000000},"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":[[2009,12]]},"DOI":"10.1007\/s10994-009-5142-6","type":"journal-article","created":{"date-parts":[[2009,9,2]],"date-time":"2009-09-02T14:28:27Z","timestamp":1251901707000},"page":"195-224","source":"Crossref","is-referenced-by-count":6,"title":["Periodic step-size adaptation in second-order gradient descent for single-pass on-line structured learning"],"prefix":"10.1007","volume":"77","author":[{"given":"Chun-Nan","family":"Hsu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Shen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Ming","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuh-Jye","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,9,3]]},"reference":[{"key":"5142_CR1","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S.-I. Amari","year":"1998","unstructured":"Amari, S.-I. (1998). Natural gradient works efficiently in learning. Neural Computation, 10, 251\u2013276.","journal-title":"Neural Computation"},{"key":"5142_CR2","first-page":"29","volume-title":"Proceedings of the 1988 connectionist models summer school","author":"S. Becker","year":"1988","unstructured":"Becker, S., & LeCun, Y. (1988). Improving the convergence of back-propagation learning with second-order methods. In Proceedings of the 1988 connectionist models summer school (pp. 29\u201337). San Mateo: Morgan Kaufman."},{"key":"5142_CR3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-75894-2","volume-title":"Adaptive algorithms and stochastic approximations","author":"A. Benveniste","year":"1990","unstructured":"Benveniste, A., Metivier, M., & Priouret, P. (1990). Adaptive algorithms and stochastic approximations. Berlin: Springer."},{"key":"5142_CR4","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/1273496.1273508","volume-title":"Proceedings of the 24th international conference on machine learning (ICML\u201907)","author":"A. Bordes","year":"2007","unstructured":"Bordes, A., Bottou, L., Gallinari, P., & Weston, J. (2007). Solving multiclass support vector machines with LaRank. In Proceedings of the 24th international conference on machine learning (ICML\u201907) (pp. 89\u201396). New York: ACM."},{"key":"5142_CR5","unstructured":"Bottou, L. (2007). The tradeoffs of large-scale learning. Tutorial, the 21st annual conference on neural information processing systems (NIPS 2007), Vancouver, BC, Canada. http:\/\/leon.bottou.org\/talks\/largescale ."},{"key":"5142_CR6","volume-title":"Advances in neural information processing systems, 20 (NIPS 2007)","author":"L. Bottou","year":"2008","unstructured":"Bottou, L., & Bousquet, O. (2008). The tradeoffs of large scale learning. In Advances in neural information processing systems, 20 (NIPS 2007). Cambridge: MIT Press."},{"key":"5142_CR7","volume-title":"Advances in neural information processing systems 16 (NIPS 2003)","author":"L. Bottou","year":"2004","unstructured":"Bottou, L., & LeCun, Y. (2004). Large scale online learning. In S. Thrun, L. Saul, & B. Sch\u00f6lkopf (Eds.), Advances in neural information processing systems 16 (NIPS 2003). Cambridge: MIT Press."},{"issue":"2","key":"5142_CR8","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1002\/asmb.538","volume":"21","author":"L. Bottou","year":"2005","unstructured":"Bottou, L., & LeCun, Y. (2005). On-line learning for very large data sets. Applied Stochastic Models in Business and Industry, 21(2), 137\u2013151.","journal-title":"Applied Stochastic Models in Business and Industry"},{"volume-title":"Large scale kernel machines","year":"2007","key":"5142_CR9","unstructured":"Bottou, L., Chapelle, O., DeCoste, D., & Weston, J. (Eds.) (2007). Large scale kernel machines. Cambridge: MIT Press."},{"key":"5142_CR10","unstructured":"Burden, R. L., & Faires, D. (1988). Numerical analysis. PWS-KENT Pub. Co."},{"key":"5142_CR11","unstructured":"Chang, C.-C., & Lin, C.-J. (2001). LIBSVM: a library for support vector machines. Software available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm ."},{"key":"5142_CR12","doi-asserted-by":"crossref","unstructured":"Chen, S. F., & Rosenfeld, R. (1999). A Gaussian prior for smoothing maximum entropy models. Technical Report CMU-CS-99-108, School of Computer Science, Carnegie Mellon University, PA, USA, Pittsburgh.","DOI":"10.21236\/ADA360974"},{"key":"5142_CR13","first-page":"1775","volume":"9","author":"M. Collins","year":"2008","unstructured":"Collins, M., Globerson, A., Koo, T., Carreras, X., & Bartlett, P. L. (2008). Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks. Journal of Machine Learning Research, 9, 1775\u20131822.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"5142_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., & Rubin, D. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39(1), 1\u201338.","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"5142_CR15","unstructured":"Fahlmann, S. E. (1988). An empirical study of learning speed in back-propagation networks. Technical Report CMU-CS-88-162, Carnegie Mellon University."},{"issue":"1","key":"5142_CR16","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/S0167-9473(99)00003-1","volume":"31","author":"C. Fraley","year":"1999","unstructured":"Fraley, C. (1999). On computing the largest fraction of missing information for the EM algorithm and the worst linear function for data augmentation. Computational Statistics and Data Analysis, 31(1), 13\u201326.","journal-title":"Computational Statistics and Data Analysis"},{"key":"5142_CR17","unstructured":"Hesterberg, T. (2005). Staggered Aitken acceleration for EM. In Proceedings of the statistical computing section of the American statistical association, Minneapolis, Minnesota, USA."},{"key":"5142_CR18","doi-asserted-by":"crossref","unstructured":"Hsu, C.-N., Huang, H.-S., & Yang, B.-H. (2006). Global and componentwise extrapolation for accelerating data mining from large incomplete data sets with the EM algorithm. In Proceedings of the sixth IEEE international conference on data mining (ICDM\u201906) (pp.\u00a0265\u2013274), Hong Kong, China.","DOI":"10.1109\/ICDM.2006.77"},{"issue":"13","key":"5142_CR19","doi-asserted-by":"crossref","first-page":"i286","DOI":"10.1093\/bioinformatics\/btn183","volume":"24","author":"C.-N. Hsu","year":"2008","unstructured":"Hsu, C.-N., Chang, Y.-M., Kuo, C.-J., Lin, Y.-S., Huang, H.-S., & Chuang, I.-F. (2008). Integrating high dimensional bi-directional parsing models for gene mention tagging. Bioinformatics, 24(13), i286\u2013i294. Proceedings of ISMB-2008.","journal-title":"Bioinformatics"},{"key":"5142_CR20","doi-asserted-by":"crossref","unstructured":"Huang, H.-S., Yang, B.-H., & Hsu, C.-N. (2005). Triple-jump acceleration for the EM algorithm. In Proceedings of the fifth IEEE international conference on data mining (ICDM\u201905) (pp.\u00a0649\u2013652).","DOI":"10.1109\/ICDM.2005.146"},{"issue":"1","key":"5142_CR21","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1007\/s10618-009-0128-3","volume":"19","author":"H.-S. Huang","year":"2009","unstructured":"Huang, H.-S., Yang, B.-H., Chang, Y.-M., & Hsu, C.-N. (2009). Global and componentwise extrapolations for accelerating training of Bayesian networks and conditional random fields. Data Mining and Knowledge Discovery, 19(1), 58\u201391.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"5142_CR22","first-page":"169","volume-title":"Advances in kernel methods: support vector learning","author":"T. Joachims","year":"1998","unstructured":"Joachims, T. (1998). Making large-scale svm learning practical. In B. Sch\u00f6lkoph, C. J. C. Burges, & A. J. Smola (Eds.), Advances in kernel methods: support vector learning (Chap. 11, pp. 169\u2013184). Cambridge: MIT Press."},{"key":"5142_CR23","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1145\/1150402.1150429","volume-title":"Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining (KDD\u201906)","author":"T. Joachims","year":"2006","unstructured":"Joachims, T. (2006). Training linear SVMs in linear time. In Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining (KDD\u201906) (pp. 217\u2013226). New York: ACM."},{"key":"5142_CR24","unstructured":"Kudo, T. (2006). CRF++: Yet another CRF toolkit. Available under LGPL from the following URL: http:\/\/crfpp.sourceforge.net\/ ."},{"key":"5142_CR25","unstructured":"Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of 18th international conference on machine learning (ICML\u201903) (pp.\u00a0282\u2013289)."},{"key":"5142_CR26","unstructured":"LeCun, Y., & Cortes, C. (1998). The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ ."},{"key":"5142_CR27","volume-title":"Neural networks: tricks of the trade","author":"Y. LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Orr, G. B., & Muller, K.-R. (1998a). Efficient backprop. In G. Orr & K.\u00a0Muller (Eds.), Neural networks: tricks of the trade. Berlin: Springer."},{"issue":"11","key":"5142_CR28","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y. LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998b). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"5142_CR29","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-46805-6_19","volume-title":"Shape, contour and grouping in computer vision","author":"Y. LeCun","year":"1999","unstructured":"LeCun, Y., Haffner, P., Bottou, L., & Bengio, Y. (1999). Object recognition with gradient-based learning. In Shape, contour and grouping in computer vision (p.\u00a0319). London: Springer."},{"key":"5142_CR30","volume-title":"Advances in neural information processing systems, 20 (NIPS 2007)","author":"N. LeRoux","year":"2008","unstructured":"LeRoux, N., Manzagol, P.-A., & Bengio, Y. (2008). Topmoumoute online natural gradient algorithm. In Advances in neural information processing systems, 20 (NIPS 2007). Cambridge: MIT Press."},{"key":"5142_CR31","doi-asserted-by":"crossref","unstructured":"Malouf, R. (2002). A comparison of algorithms for maximum entropy parameter estimation. In Proceedings of the sixth conference on natural language learning (CoNLL-2002) (pp. 49\u201355).","DOI":"10.3115\/1118853.1118871"},{"key":"5142_CR32","series-title":"Wiley series in probability and statistics","volume-title":"The EM algorithm and extensions","author":"G. J. McLachlan","year":"1997","unstructured":"McLachlan, G. J., & Krishnan, T. (1997). The EM algorithm and extensions. Wiley series in probability and statistics. New York: Wiley-Interscience."},{"key":"5142_CR33","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/0024-3795(94)90363-8","volume":"199","author":"X.-L. Meng","year":"1994","unstructured":"Meng, X.-L., & Rubin, D. B. (1994). On the global and componentwise rates of convergence of the EM algorithm. Linear Algebra and Its Applications, 199, 413\u2013425.","journal-title":"Linear Algebra and Its Applications"},{"key":"5142_CR34","first-page":"63","volume-title":"On-line learning in neural networks","author":"N. Murata","year":"1998","unstructured":"Murata, N. (1998). A statistical study of on-line learning. In On-line learning in neural networks (pp. 63\u201392). Cambridge: Cambridge University Press."},{"issue":"1","key":"5142_CR35","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0165-1684(98)00206-0","volume":"74","author":"N. Murata","year":"1999","unstructured":"Murata, N., & Amari, S.-I. (1999). Statistical analysis of learning dynamics. Signal Processing, 74(1), 3\u201328.","journal-title":"Signal Processing"},{"key":"5142_CR36","doi-asserted-by":"crossref","DOI":"10.1007\/b98874","volume-title":"Numerical optimization","author":"J. Nocedal","year":"1999","unstructured":"Nocedal, J., & Wright, S. J. (1999). Numerical optimization. Berlin: Springer."},{"key":"5142_CR37","volume-title":"Iterative solution of nonlinear equations in several variables","author":"J. M. Ortega","year":"1970","unstructured":"Ortega, J. M., & Rheinboldt, W. C. (1970). Iterative solution of nonlinear equations in several variables. San Diego: Academic Press."},{"key":"5142_CR38","unstructured":"Salakhutdinov, R., & Roweis, S. (2003). Adaptive overrelaxed bound optimization methods. In Proceedings of the twentieth international conference on machine learning (ICML\u201903) (pp.\u00a0664\u2013671)."},{"key":"5142_CR39","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821862","volume-title":"Analysis of incomplete multivariate data","author":"J. L. Schafer","year":"1997","unstructured":"Schafer, J. L. (1997). Analysis of incomplete multivariate data. New York: Chapman and Hall."},{"key":"5142_CR40","doi-asserted-by":"crossref","unstructured":"Schraudolph, N. N., & Graepel, T. (2002). Conjugate directions for stochastic gradient descent. In Proceedings of international conference on artificial neural networks (ICANN\u201902) (pp.\u00a01351\u20131358).","DOI":"10.1007\/3-540-46084-5_218"},{"key":"5142_CR41","unstructured":"Schraudolph, N. N., Yu, J., & G\u00fcnter, S. (2007). A stochastic quasi-newton method for online convex optimization. In Proceedings of the 11th international conference on artificial intelligence and statistics (AISTATS 2007), San Juan, Puerto Rico."},{"key":"5142_CR42","doi-asserted-by":"crossref","unstructured":"Settles, B. (2004). Biomedical named entity recognition using conditional random fields and novel feature sets. In Proceedings of the joint workshop on natural language processing in biomedicine and its applications (JNLPBA-2004) (pp.\u00a0104\u2013107).","DOI":"10.3115\/1567594.1567618"},{"key":"5142_CR43","doi-asserted-by":"crossref","unstructured":"Sha, F., & Pereira, F. (2003). Shallow parsing with conditional random fields. In Proceedings of human language technology, the North American chapter of the association for computational linguistics (NAACL\u201903) (pp.\u00a0213\u2013220).","DOI":"10.3115\/1073445.1073473"},{"key":"5142_CR44","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1145\/1273496.1273598","volume-title":"ICML\u201907: Proceedings of the 24th international conference on machine learning","author":"S. Shalev-Shwartz","year":"2007","unstructured":"Shalev-Shwartz, S., Singer, Y., & Srebro, N. (2007). Pegasos: Primal Estimated sub-GrAdient SOlver for SVM. In ICML\u201907: Proceedings of the 24th international conference on machine learning (pp. 807\u2013814). New York: ACM."},{"key":"5142_CR45","doi-asserted-by":"crossref","DOI":"10.1002\/0471722138","volume-title":"Introduction to stochastic search and optimization: estimation, simulation and control","author":"J. C. Spall","year":"2003","unstructured":"Spall, J. C. (2003). Introduction to stochastic search and optimization: estimation, simulation and control. New York: Wiley-Interscience."},{"key":"5142_CR46","doi-asserted-by":"crossref","unstructured":"Taskar, B. (2005). Learning structured prediction models: a large margin approach. Ph.D. thesis, Stanford University, Stanford, CA, USA. Adviser-Daphne Koller.","DOI":"10.1145\/1102351.1102464"},{"key":"5142_CR47","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1145\/1102351.1102464","volume-title":"Proceedings of the 22nd international conference on machine learning (ICML\u201905)","author":"B. Taskar","year":"2005","unstructured":"Taskar, B., Chatalbashev, V., Koller, D., & Guestrin, C. (2005). Learning structured prediction models: a large margin approach. In Proceedings of the 22nd international conference on machine learning (ICML\u201905) (pp. 896\u2013903). New York: ACM."},{"key":"5142_CR48","volume-title":"Iterative methods for the solution of equations","author":"J. Traub","year":"1964","unstructured":"Traub, J. (1964). Iterative methods for the solution of equations. Englewood Cliffs: Prentice Hall."},{"key":"5142_CR49","first-page":"1453","volume":"6","author":"I. Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., & Altun, Y. (2005). Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6, 1453\u20131484.","journal-title":"Journal of Machine Learning Research"},{"key":"5142_CR50","doi-asserted-by":"crossref","unstructured":"Vishwanathan, S., Schraudolph, N. N., Schmidt, M. W., & Murphy, K. P. (2006a). Accelerated training of conditional random fields with stochastic gradient methods. In Proceedings of the 23rd international conference on machine learning (ICML\u201906), Pittsburgh, PA, USA.","DOI":"10.1145\/1143844.1143966"},{"key":"5142_CR51","first-page":"1107","volume":"7","author":"S. Vishwanathan","year":"2006","unstructured":"Vishwanathan, S., Schraudolph, N. N., & Smola, A. J. (2006b). Step size adaptation in reproducing kernel Hilbert space. Journal of Machine Learning Research, 7, 1107\u20131133.","journal-title":"Journal of Machine Learning Research"},{"key":"5142_CR52","doi-asserted-by":"crossref","unstructured":"Widrow, B., & Hoff, M. E. (1960). Adaptive switching circuits. In 1960 IRE WESCON convention record (pp. 96\u2013104), New York.","DOI":"10.21236\/AD0241531"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-009-5142-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-009-5142-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-009-5142-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T23:29:42Z","timestamp":1739316582000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-009-5142-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,9,3]]},"references-count":52,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2009,12]]}},"alternative-id":["5142"],"URL":"https:\/\/doi.org\/10.1007\/s10994-009-5142-6","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2009,9,3]]}}}