Confidence bounds for the generalization performances of linear combination of functions
Gérald Gavin · 1999
This paper presents new results about confidence bounds on the generalization performances of linear combination of functions belonging to a set H. It is shown that when learning with monomial loss functions, the probability that the generalization error be greater than the empirical error plus /spl epsiv/, depends on the covering number of H and the magnitude of the coefficients of the combination. The classification case is studied by approximating a step function with polynomials.