zbMATH — the first resource for mathematics

“Local” vs. “global” parameters – breaking the Gaussian complexity barrier. (English) Zbl 1459.62054
Summary: We show that if \(F\) is a convex class of functions that is \(L\)-sub-Gaussian, the error rate of learning problems generated by independent noise is equivalent to a fixed point determined by “local” covering estimates of the class (i.e., the covering number at a specific level), rather than by the Gaussian average, which takes into account the structure of \(F\) at an arbitrarily small scale. To that end, we establish new sharp upper and lower estimates on the error rate in such learning problems.

62G08 Nonparametric regression and quantile regression
62C20 Minimax procedures in statistical decision theory
60G15 Gaussian processes
PDF BibTeX Cite
Full Text: DOI arXiv