Abstract | ||
---|---|---|
We study learning algorithms for classification generated by regularization schemes in reproducing kernel Hilbert spaces associated with a general convex loss function in a non-i.i.d. process. Error analysis is studied and our main purpose is to provide an elaborate capacity dependent error bounds by applying concentration techniques involving the @?^2-empirical covering numbers. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.mcm.2011.03.042 | Mathematical and Computer Modelling |
Keywords | Field | DocType |
dependent error bound,capacity dependent error bounds,error analysis,general convex loss function,learning theory,regularization scheme,regularized classification,reproducing kernel hilbert spaces,ℓ 2 -empirical covering number,β -mixing sequence,main purpose,reproducing kernel hilbert space,elaborate capacity,concentration technique,loss function | Kernel (linear algebra),Hilbert space,Mathematical optimization,Mathematical analysis,Kernel embedding of distributions,Kernel principal component analysis,Regularization (mathematics),Representer theorem,Mathematics,Reproducing kernel Hilbert space,Kernel (statistics) | Journal |
Volume | Issue | ISSN |
54 | 5-6 | Mathematical and Computer Modelling |
Citations | PageRank | References |
3 | 0.45 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zheng-Chu Guo | 1 | 26 | 2.66 |
Lei Shi | 2 | 104 | 8.13 |