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...

Full description

Bibliographic Details
Main Author: Kur, Gil
Other Authors: Rakhlin, Alexander
Format: Thesis
Published: Massachusetts Institute of Technology 2023
Online Access:https://hdl.handle.net/1721.1/152867