{"type":"ScholarlyArticle","title":"Maximum Margin Coresets for Active and Noise Tolerant Learning","authors":[{"name":"Sariel Har-Peled","slug":"sariel-har-peled","given":"Sariel","family":"Har-Peled","affiliation":"Department of Computer Science Yahoo! Inc . University of Illinois at Urbana-Champaign Santa Clara , CA; University of Illinois Computer Science Department."},{"name":"Dan Roth","slug":"dan-roth","given":"Dan","family":"Roth","affiliation":"Department of Computer Science Yahoo! Inc . University of Illinois at Urbana-Champaign Santa Clara , CA"},{"name":"Dav Zimak","slug":"dav-zimak","given":"Dav","family":"Zimak","affiliation":"Department of Computer Science Yahoo! Inc . University of Illinois at Urbana-Champaign Santa Clara , CA"}],"abstract":"We study the problem of learning large margin halfspaces in various settings using coresets and show that coresets are a widely applicable tool for large margin learning. A large margin coreset is a subset of the input data sufficient for approximating the true maximum margin solution. In this work, we provide a direct algorithm and analysis for constructing large margin coresets. We show various applications including a novel coreset based analysis of large margin active learning and a polynomial time (in the number of input data and the amount of noise) algorithm for agnostic learning in the presence of outlier noise. We also highlight a simple extension to multi-class classification problems and structured output learning.","doi":null,"url":"https://ijcai.org/proceedings/2007/134","pdf":"https://ijcai.org/proceedings/2007/0134.pdf","markdown":"https://ijcai.org/proceedings/2007/134.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/134","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":134,"pages":{"first":836,"last":840},"keywords":[],"videos":[],"references":[{"position":1,"raw":"D. Angluin. Queries and concept learning. Machine Learn- ing, 2(4):319-342, 1987.","title":"Queries and concept learning","authors":"D Angluin","year":"1987","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"M. Badoiu and K.L. Clarkson. Smaller core-sets for balls. In SODA, pages 801-802, 2003.","title":"Smaller core-sets for balls","authors":"M Badoiu, K L Clarkson","year":"2003","venue":"SODA","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"C. Campbell, N. Cristianini, and A.J. Smola. Query learning with large margin classifiers. In Proceedings of the Seven- teeth ICML, pages 111-118, 2000.","title":"Query learning with large margin classifiers","authors":"C Campbell, N Cristianini, A J Smola","year":"2000","venue":"Proceedings of the Seventeeth ICML","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"S. Dasgupta. Analysis of a greedy active learning strategy. In NIPS, volume 17, pages 337-344. MIT Press, 2005.","title":"Analysis of a greedy active learning strategy","authors":"S Dasgupta","year":"2005","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"Y. Freund and R.E. Schapire. A decision-theoretic general- ization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 55(1):119-139, 1997.","title":"A decision-theoretic generalization of on-line learning and an application to boosting","authors":"Y Freund, R E Schapire","year":"1997","venue":"J. Comput. Syst. Sci","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"C. Gentile. A new approximate maximal margin classification algorithm. JMLR, 2:213-242, 2001.","title":"A new approximate maximal margin classification algorithm","authors":"C Gentile","year":"2001","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"T. Joachims. Training linear svms in linear time. In Proceed- ings of the Twelfth ACM SIGKDD, New York, 2006.","title":"Training linear svms in linear time","authors":"T Joachims","year":"2006","venue":"Proceedings of the Twelfth ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"M. Kearns, M. Li, L. Pitt, and L. Valiant. Recent results on boolean concept learning. In Proceedings of the Fourth International Workshop on Machine Learning, pages 337- 352, 1987.","title":"Recent results on boolean concept learning","authors":"M Kearns, M Li, L Pitt, L Valiant","year":"1987","venue":"Proceedings of the Fourth International Workshop on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"A. Kowalczyk. Maximal margin perceptron. In Advances in Large Margin Classifiers. MIT Press, Cambridge MA, 2000.","title":"Maximal margin perceptron","authors":"A Kowalczyk","year":"2000","venue":"Advances in Large Margin Classifiers","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"M. Kearns and R. Schapire. Efficient distribution-free learn- ing of probabilistic concepts. In Computational Learn- ing Theory and Natural Learning Systems, Constraints and Prospect, volume 1. The MIT Press, 1994.","title":"Efficient distribution-free learning of probabilistic concepts","authors":"M Kearns, R Schapire","year":"1994","venue":"Computational Learning Theory and Natural Learning Systems, Constraints and Prospect","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Y. Li and P.M. Long. The relaxed online maximum margin algorithm. Machine Learning, 46(1-3):361-387, 2002.","title":"The relaxed online maximum margin algorithm","authors":"Y Li, P M Long","year":"2002","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"E. Osuna, R. Freund, and F. Girosi. Improved training algo- rithm for support vector machines. NNSP, 1997.","title":"Improved training algorithm for support vector machines","authors":"E Osuna, R Freund, F Girosi","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"J. Platt. Sequential minimal optimization: A fast algorithm for training support vector machines. Technical Report 98- 14, Microsoft Research, April 1998.","title":"Sequential minimal optimization: A fast algorithm for training support vector machines","authors":"J Platt","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"I. Tsochantaridis, T. Hofmann, T. Joachims, and Y. Altun. Support vector machine learning for interdependent and structured output spaces. In Proceedings of the twenty-first ICML, page 104. ACM Press, 2004.","title":"Support vector machine learning for interdependent and structured output spaces","authors":"I Tsochantaridis, T Hofmann, T Joachims, Y Altun","year":"2004","venue":"Proceedings of the twenty-first ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"S. Tong and D. Koller. Support vector machine active learning with applications to text classification. JMLR, 2:45-66, 2002.","title":"Support vector machine active learning with applications to text classification","authors":"S Tong, D Koller","year":"2002","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"I.W. Tsang, J.T. Kwok, and P. Cheung. Core vector machines: Fast svm training on very large data sets. JMLR, 6:363- 392, 2005.","title":"Core vector machines: Fast svm training on very large data sets","authors":"I W Tsang, J T Kwok, P Cheung","year":"2005","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"V.N. Vapnik. Estimation of Dependences Based on Empirical Data. Springer Series in Statistics. Springer, New York, 1982.","title":"Estimation of Dependences Based on Empirical Data","authors":"V N Vapnik","year":"1982","venue":"Springer Series in Statistics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"V.N. Vapnik. The nature of statistical learning theory. Springer Verlag, Heidelberg, DE, 1995.","title":"The nature of statistical learning theory","authors":"V N Vapnik","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}