Explicit overall risk minimization transductive bound
Sergio Decherchi, Paolo Gastaldo, Sandro Ridella, Rodolfo Zunino · 2008
Aside classical inductive methods transduction has reached an always increasing attention from the scientific community because of its learning paradigm. Explicit error bounds for inductive methods are well established results and stem from Vapnik theory or Rademacher complexity. In this work we address the problem of building an explicit form of the transductive bound presented in Vapnik Overall Risk Minimization approach.