On The Performance Of The Maximum Likelihood Over Large Models

This dissertation investigates non-parametric regression over large function classes, specifically, non-Donsker classes. We will present the concept of non-Donsker classes and study the statistical performance of Least Squares Estimator (LSE) --- which also serves as the Maximum Likelihood Estimato...

תיאור מלא

מידע ביבליוגרפי
מחבר ראשי: Kur, Gil
מחברים אחרים: Rakhlin, Alexander
פורמט: Thesis
יצא לאור: Massachusetts Institute of Technology 2023
גישה מקוונת:https://hdl.handle.net/1721.1/152867