Back to search

Georgia Institute of Technology

Statistical Theory for Neural Network-Based Learning

Abstract

dc:description.abstract

In Chapter 1, we introduce the general problem of binary classification and the significance of studying statistical properties of neural network-based classifiers. In addition, we include a high-level overview of the main results in this thesis along with a brief review of relevant literature. In Chapter 2, we provide the necessary technical preparations for the statement and proofs of the results in the rest of the thesis. Specifically, we define the classification problem and the space of neural networks, give a short introduction to concepts from rate distortion theory used in Chapter 4, and define the Barron approximation space used in Chapter 5. Furthermore, we conclude with a discussion of the relationship between regression and classification and related results from the literature. In Chapter 3, we show that random classifiers based on finitely wide and deep neural networks are consistent for a very general class of distributions. Consistency is a highly desirable property for a sequence of classifiers that guarantees that the classification risk converges to the smallest possible risk. This result improves the classical result of Farago and Lugosi (1993) by extending the consistency property for shallow, underparametrized neural networks with sigmoid activations to wide and deep ReLU neural networks without complexity constraints. In Chapter 4, we give several convergence rate guarantees of the excess classification risk for a semiparametric model of distributions indexed by Borel probability measures on [0, 1]d and regression functions belonging to L2 class of functions with finite Kolmogorov-Donoho optimal exponents. Furthermore, we give explicit characterizations of distributional regimes in which neural network classifiers are minimax optimal. In Chapter 5, we show that for a semiparametric model of distributions defined by regular marginal distributions and regression functions that locally belong to the Barron approximation space, neural network classifiers achieve a rate of n(1+α)/(3(2+α)). We also show that this rate is minimax optimal up to a logarithmic factor.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Industrial and Systems Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ko, Hyunouk Andy
Advisor dc:contributor.advisor
  • Huo, Xiaoming
Committee members dc:contributor.committeemember
  • Xie, Yao
  • Yang, Shihao
  • Zhilova, Mayya
  • Mei, Yajun

Subjects

dc:subject × 2

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/76940

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ko, Hyunouk Andy. Statistical Theory for Neural Network-Based Learning. Doctoral thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/76940