{"product_id":"improved-classification-rates-for-localized-algorithms-under-margin-conditions-9783658295905","title":"Improved Classification Rates for Localized Algorithms Under Margin Conditions","description":"\u003cp\u003e • Author(s): Ingrid Karin Blaschzyk\u003cbr\u003e • Publisher: Springer\u003cbr\u003e • Publisher Imprint: Springer Spektrum\u003cbr\u003e • BISAC: Applied\u003c\/p\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eFrom the Back Cover\u003c\/b\u003e\u003cbr\u003eSupport vector machines (SVMs) are one of the most successful algorithms on small and medium-sized data sets, but on large-scale data sets their training and predictions become computationally infeasible. The author considers a spatially defined data chunking method for large-scale learning problems, leading to so-called localized SVMs, and implements an in-depth mathematical analysis with theoretical guarantees, which in particular include classification rates. The statistical analysis relies on a new and simple partitioning based technique and takes well-known margin conditions into account that describe the behavior of the data-generating distribution. It turns out that the rates outperform known rates of several other learning algorithms under suitable sets of assumptions. From a practical point of view, the author shows that a common training and validation procedure achieves the theoretical rates adaptively, that is, without knowing the margin parameters in advance.\u003c\/p\u003e\u003cp\u003e\u003cb\u003eContents\u003c\/b\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e\u003c\/p\u003e\u003cul\u003e\n\u003cli\u003eIntroduction to Statistical Learning Theory\u003c\/li\u003e\n\u003cli\u003eHistogram Rule: Oracle Inequality and Learning Rates\u003c\/li\u003e\n\u003cli\u003eLocalized SVMs: Oracle Inequalities and Learning Rates\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eTarget Groups\u003c\/b\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003eResearchers, students, and practitioners in the fields of mathematics and computer sciences who focus on machine learning or statistical learning theory\u003c\/p\u003e \u003cp\u003e\u003cb\u003eThe Author\u003c\/b\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003eIngrid Karin Blaschzyk is a postdoctoral researcher in the Department of Mathematics at the University of Stuttgart, Germany.\u003c\/p\u003e","brand":"Springer","offers":[{"title":"Paperback","offer_id":45277941104791,"sku":"9783658295905","price":3639.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0666\/3471\/1191\/files\/9783658295905.webp?v=1769289615","url":"https:\/\/atlanticbooks.com\/products\/improved-classification-rates-for-localized-algorithms-under-margin-conditions-9783658295905","provider":"Atlantic Books","version":"1.0","type":"link"}