Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/231542
Title: FUNDAMENTAL PERFORMANCE LIMITS OF STATISTICAL PROBLEMS: FROM DETECTION THEORY TO SEMI-SUPERVISED LEARNING
Authors: HE HAIYUN
ORCID iD:   orcid.org/0000-0002-1797-6101
Keywords: Information theory, Statistical learning, Distributed detection, Change-point detection, Semi-supervised learning, Generalization error
Issue Date: 18-Apr-2022
Citation: HE HAIYUN (2022-04-18). FUNDAMENTAL PERFORMANCE LIMITS OF STATISTICAL PROBLEMS: FROM DETECTION THEORY TO SEMI-SUPERVISED LEARNING. ScholarBank@NUS Repository.
Abstract: Designing and analyzing close-to-optimal mechanisms to infer or learn useful information from raw data is of tremendous significance in this digital and data-rich era. This thesis explores the fundamental performance limits of three classes of statistical problems—distributed detection, change-point detection and the generalization capabilities of semi-supervised learning (SSL). For the detection problems, in contrast to classical works assuming known underlying data distributions, we consider the practical scenario where training data samples are available instead. We derive the asymptotically optimal detector and error exponent for distributed detection (or detection confidence width for change-point detection). For the statistical learning problem, we are motivated to mitigate the high cost of acquiring labelled data. We analyze the fundamental limits of SSL which makes use of both labelled and unlabelled training data. Using information-theoretic principles, we investigate the generalization error, which quantifies the extent to which the algorithms overfit to the training data.
URI: https://scholarbank.nus.edu.sg/handle/10635/231542
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
HeHY.pdf4.83 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

18
checked on Dec 1, 2022

Download(s)

4
checked on Dec 1, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.