Unit:
Κατεύθυνση Στατιστική και Επιχειρησιακή ΈρευναLibrary of the School of Science
Author:
Thivaiou Paraskevi
Supervisors info:
Τρεβεζας Σάμης, Λέκτορας, Μαθηματικό, ΕΚΠΑ
Μπουρνετας Απόστολος, Καθηγητής, Μαθηματικο, ΕΚΠΑ
Μελιγκοτσιδου Λουκια, Επίκουρη Καθηγήτρια, Μαθηματικό, ΕΚΠΑ
Original Title:
Hamiltonian Monte Carlo and Applications in Bayesian Linear Regression
Translated title:
Hamiltonian Monte Carlo and Applications in Bayesian Linear Regression
Summary:
The HMC algorithm is an upgration of the well known MCMC Algorithm, used in many applications based on Bayesian data analysis. This thesis analyzes the basic algorithm of the HMC, the pros and cons of it and provides two applications, one compering the classic Random Walk algorithm of MCMC to the upgrade form of HMC, and a second one showing how HMC works when analyzing data compering to general linear regression models.
Main subject category:
Science
Keywords:
HMC, Hamiltonian Monte Carlo, Random Walk, Bayesian Analysis
File:
File access is restricted only to the intranet of UoA.
Paraskevi Thivaiou_Thesis_Hamiltonian monte carlo.pdf
20 MB
File access is restricted only to the intranet of UoA.
