Convergence rates of generalization errors for margin-based classification

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


This paper develops a general approach to quantifying the size of generalization errors for margin-based classification. A trade-off between geometric margins and training errors is exhibited along with the complexity of a binary classification problem. Consequently, this results in dealing with learning theory in a broader framework, in particular, of handling both convex and non-convex margin classifiers, among which includes, support vector machines, kernel logistic regression, and ψ-learning. Examples for both linear and nonlinear classifications are provided.

Original languageEnglish
Pages (from-to)2543-2551
Number of pages9
JournalJournal of Statistical Planning and Inference
Issue number8
StatePublished - 1 Aug 2009


  • Classification
  • Convex and non-convex loss
  • Empirical process
  • Statistical learning theory


Dive into the research topics of 'Convergence rates of generalization errors for margin-based classification'. Together they form a unique fingerprint.

Cite this