Content area

Abstract

Probability theory and probabilistic algorithms form the fundamental bedrock of modern data science and machine learning. These mathematical frameworks provide essential tools for tackling contemporary data challenges, notably high dimensionality and intricate dependency structures among data points. This thesis investigates three distinct yet interconnected probabilistic problems. The first addresses dimensionality reduction through the lens of generalized t-SNE. The second confronts complex dependencies by exploring Markov Random Fields in conjunction with the Lovász Local Lemma. Finally, the third problem synthesizes challenges of both dimensionality and dependency via Variational Factor Analysis. To ensure accessibility for a broader audience, an introductory chapter will provide requisite background knowledge on these core concepts and their interplay.

Details

1010268
Business indexing term
Title
Generalized t-SNE and Beyond: Probabilistic Methods for Dimensionality Reduction, Combinatorial Optimization, and Machine Learning
Author
Gu, Yi  VIAFID ORCID Logo 
Number of pages
244
Publication year
2025
Degree date
2025
School code
0163
Source
DAI-B 87/3(E), Dissertation Abstracts International
ISBN
9798291588147
Committee member
Hsu, Elton; Zabell, Sandy
University/institution
Northwestern University
Department
Mathematics
University location
United States -- Illinois
Degree
Ph.D.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
32114645
ProQuest document ID
3245383260
Document URL
https://www.proquest.com/dissertations-theses/generalized-t-sne-beyond-probabilistic-methods/docview/3245383260/se-2?accountid=208611
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Database
ProQuest One Academic