9月18、22日 Sergei V. Pereverzev教授学术报告

发布时间:2013-09-10

1.
题 目：Parameter choice strategies for multi-penalty regularization

报告人：Sergei V. Pereverzev, Professor
(Johann Radon Institute for Computational and Applied Mathematics, Linz, Austria)

时 间： 9月18日（周三） 下午4:00-5:00

地 点： 数学楼104室

Abstract:
The widespread applicability of the multi-penalty regularization is limited by the fact that theoretically optimal rate of reconstruction for a given problem can be realized by a one-parameter counterpart, provided that relevant information on the problem is available and taken into account in the regularization. In this talk, we explore the situation, where no such information is given, but still accuracy of optimal order can be guaranteed by employing multi-penalty regularization. Our focus is on the analysis and the justification of an a posteriori parameter choice rule for such a regularization scheme. First we present a modified version of the discrepancy principle within the multi-penalty regularization framework. As a consequence we provide a theoretical justification to the multi-penalty regularization scheme equipped with the a posteriori parameter choice rule. We then establish a fast numerical realization of the proposed discrepancy principle based on a model function approximation. Finally, we provide extensive numerical results which confirm and support the theoretical estimates and illustrate the robustness and the superiority of the proposed scheme compared to the “classical” regularization methods.
Joint research with Massimo Fornasier (TU Munich) and Vareriya Naumova (RICAM, Linz)


2.
题 目：A Meta-Learning Approach to the Regularized Learning – Case Study: Blood Glucose Prediction

报告人：Sergei V. Pereverzev, Professor
(Johann Radon Institute for Computational and Applied Mathematics, Linz, Austria)

时 间： 9月22日（周日） 下午4:00-5:00

地 点：数学楼104室

Abstract:
In this talk we present a new scheme of a kernel-based regularization learning algorithm, in which the kernel and the regularization parameter are adaptively chosen on the base of previous experience with similar learning tasks. The construction of such scheme is motivated by the problem of prediction of the blood glucose levels of diabetic patients. We describe how the proposed scheme can be used for this problem and report the results of the tests with real clinical data as well as compare them with existing literature.
Joint research with Vareriya Naumova and Sivananthan Samath (RICAM, Linz)

报告人简介：
http://www.ricam.oeaw.ac.at/people/page.cgi?firstn=Sergei;lastn=Pereverzyev

欢迎有兴趣的师生前来参加！