Back to search

Purdue University

Computationally Efficient Nonparametric Testing

Abstract

dc:description.abstract

A common challenge in nonparametric inference is its high computational complexity when data volume is large. In this thesis, I will introduce novel computationally efficient nonparametric testing methods. Firstly, we develop a computationally efficient nonparametric testing by employing a random projection strategy. In the specific kernel ridge regression setup, a simple distance-based test statistic is proposed. Notably, we derive the minimum number of random projections that is sufficient for achieving testing optimality in terms of the minimax rate. An adaptive testing procedure is further established without prior knowledge of regularity. One technical contribution is to establish upper bounds for a range of tail sums of empirical kernel eigenvalues. Simulations and real data analysis are conducted to further support our theory. Secondly, we study nonparametric testing under algorithmic regularization. Early stopping of iterative algorithms is an algorithmic regularization method to avoid over-fitting in estimation and classification. In this paper, we show that early stopping can also be applied to obtain the minimax optimal testing in a general non-parametric setup. Specifically, a distance-based test statistic is obtained based on an iterated estimate produced by functional gradient descent algorithms in a reproducing kernel Hilbert space. A notable contribution is to establish a “sharp” stopping rule: when the number of iterations achieves an optimal order, testing optimality is achievable; otherwise, testing optimality becomes impossible. As a by-product, a similar sharpness result is also derived for minimax optimal estimation under early stopping. All obtained results hold for various kernel classes, including Sobolev smoothness classes and Gaussian kernel classes.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy (PhD)
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Statistics

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Liu, Meimei
Contributors dc:contributor
  • Guang Cheng
  • Anirban Dasgupta
  • Chuanhai Liu
  • Chong Gu

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Purdue University
Base URL
docs.lib.purdue.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Liu, Meimei. Computationally Efficient Nonparametric Testing. Dissertation thesis, https://docs.lib.purdue.edu/open_access_dissertations/2003