{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/linear-maximum-margin-classifier-for-learning","title":"Linear Maximum Margin Classifier for Learning from Uncertain Data","arxiv_id":"1504.03892","date":"2015-04-15","proceeding":null,"authors":["Christos Tzelepis","Vasileios Mezaris","Ioannis Patras"],"abstract":"In this paper, we propose a maximum margin classifier that deals with\nuncertainty in data input. More specifically, we reformulate the SVM framework\nsuch that each training example can be modeled by a multi-dimensional Gaussian\ndistribution described by its mean vector and its covariance matrix -- the\nlatter modeling the uncertainty. We address the classification problem and\ndefine a cost function that is the expected value of the classical SVM cost\nwhen data samples are drawn from the multi-dimensional Gaussian distributions\nthat form the set of the training examples. Our formulation approximates the\nclassical SVM formulation when the training examples are isotropic Gaussians\nwith variance tending to zero. We arrive at a convex optimization problem,\nwhich we solve efficiently in the primal form using a stochastic gradient\ndescent approach. The resulting classifier, which we name SVM with Gaussian\nSample Uncertainty (SVM-GSU), is tested on synthetic data and five publicly\navailable and popular datasets; namely, the MNIST, WDBC, DEAP, TV News Channel\nCommercial Detection, and TRECVID MED datasets. Experimental results verify the\neffectiveness of the proposed method.","url_abs":"http://arxiv.org/abs/1504.03892v2","url_pdf":"http://arxiv.org/pdf/1504.03892v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"linear-maximum-margin-classifier-for-learning","repo_url":"https://github.com/chi0tzp/svm-gsu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.03892","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}