Generalization Guarantees for a Binary Classi cation Framework for Two-Stage Multiple Kernel Learning
نویسنده
چکیده
We present generalization bounds for the TS-MKL framework for two stage multiple kernel learning. We also present bounds for sparse kernel learning formulations within the TS-MKL framework.
منابع مشابه
Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning
We present generalization bounds for the TS-MKL framework for two stage multiple kernel learning. We also present bounds for sparse kernel learning formulations within the TS-MKL framework.
متن کاملSupport Vector Learning for Fuzzy Rule - Based Classi cation Systems
|To design a fuzzy rule-based classi cation system (fuzzy classi er) with good generalization ability in a high dimensional feature space has been an active research topic for a long time. As a powerful machine learning approach for pattern recognition problems, support vector machine (SVM) is known to have good generalization ability. More importantly, an SVM can work very well on a high (or e...
متن کاملLearning to Compare using Operator-Valued Large-Margin Classi ers
The proposed method uses homonymous and heteronymous examplepairs to train a linear preprocessor on a kernel-induced Hilbert space. The algorithm seeks to optimize the expected performance of elementary classi ers to be generated from single future training examples. The method is justi ed by PAC-style generalization guarantees and the resulting algorithm has been tested on problems of geometri...
متن کاملMultiple Kernel Learning: A Unifying Probabilistic Viewpoint Multiple Kernel Learning: A Unifying Probabilistic Viewpoint
We present a probabilistic viewpoint to multiple kernel learning unifying well-known regularised risk approaches and recent advances in approximate Bayesian inference relaxations. The framework proposes a general objective function suitable for regression, robust regression and classi cation that is lower bound of the marginal likelihood and contains many regularised risk approaches as special ...
متن کاملThe Rademacher Complexity of Linear Transformation Classes
Bounds are given for the empirical and expected Rademacher complexity of classes of linear transformations from a Hilbert space H to a nite dimensional space. The results imply generalization guarantees for graph regularization and multi-task subspace learning. 1 Introduction Rademacher averages have been introduced to learning theory as an e¢ cient complexity measure for function classes, mot...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013