We present sharp bounds on the risk of the empirical minimization algorithm under mild assumptions on the class. We introduce the notion of isomorphic coordinate projections and show that this leads to a sharper error bound than the best previously known. The quantity which governs this bound on the empirical minimizer is the largest fixed point of the function ζn(r) = Esup{|Ef - Enf |f ε F, Ef = r}. We prove that this is the best estimate one can obtain using "structural results", and that it is possible to estimate the error rate from data. We then prove that the bound on the empirical minimization algorithm can be improved further by a direct analysis, and that the correct error rate is the maximizer of ζn(r) - r, where ζn(r) = Esup{Ef - Enf: f ε F, Ef = r}.
CITATION STYLE
Bartlett, P. L., Mendelson, S., & Philips, P. (2004). Local complexities for empirical risk minimization. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3120, pp. 270–284). Springer Verlag. https://doi.org/10.1007/978-3-540-27819-1_19
Mendeley helps you to discover research relevant for your work.