Statistical mechanics of learning with soft margin classifiers
نویسندگان
چکیده
منابع مشابه
Statistical Mechanics of Soft Margin Classifiers
We study the typical learning properties of the recently introduced Soft Margin Classifiers (SMCs), learning realizable and unrealizable tasks, with the tools of Statistical Mechanics. We derive analytically the behaviour of the learning curves in the regime of very large training sets. We obtain exponential and power laws for the decay of the generalization error towards the asymptotic value, ...
متن کاملLearning curves for Soft Margin Classifiers
Typical learning curves for Soft Margin Classifiers (SMCs) learning both realizable and unrealizable tasks are determined using the tools of Statistical Mechanics. We derive the analytical behaviour of the learning curves in the regimes of small and large training sets. The generalization errors present different decay laws towards the asymptotic values as a function of the training set size, d...
متن کاملOnline Learning of Approximate Maximum Margin Classifiers with Biases
We consider online learning of linear classifiers which approximately maximize the 2-norm margin. Given a linearly separable sequence of instances, typical online learning algorithms such as Perceptron and its variants, map them into an augmented space with an extra dimension, so that those instances are separated by a linear classifier without a constant bias term. However, this mapping might ...
متن کاملOnline Learning of Maximum p-Norm Margin Classifiers with Bias
We propose a new online learning algorithm which provably approximates maximum margin classifiers with bias, where the margin is defined in terms of p-norm distance. Although learning of linear classifiers with bias can be reduced to learning of those without bias, the known reduction might lose the margin and slow down the convergence of online learning algorithms. Our algorithm, unlike previo...
متن کاملLearning Similarity with Operator-valued Large-margin Classifiers
A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifiers to the setting of Hilbert-Schmidt operators leads to dimension free bounds on a risk functional for linear representations and motivates a regularized objective functional. Minimization of this objective is effected...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Physical Review E
سال: 2001
ISSN: 1063-651X,1095-3787
DOI: 10.1103/physreve.64.031907