The Automatic Statistician: A Relational Perspective

DC Field Value Language
dc.contributor.advisor Choi, Jaesik - Hwang, Yunseong - 2016-02-05T16:31:12Z - 2016-02-05T16:31:12Z - 2016-02 -
dc.identifier.other 000002237195 -
dc.identifier.uri en_US
dc.identifier.uri -
dc.description Department of Computer Engineering -
dc.description.abstract Gaussian Processes (GPs) provide a general and analytically tractable way of capturing complex time-varying, nonparametric functions. The time varying parameters of GPs can be explained as a composition of base kernels such as linear, smoothness or periodicity in that covariance kernels are closed under addition and multiplication. The Automatic Bayesian Covariance Discovery (ABCD) system constructs natural-language description of time-series data by treating unknown time-series data nonparametrically using GPs. Unfortunately, learning a composite covariance kernel with a single time-series dataset often results in less informative kernels instead of finding qualitative distinct descriptions. We address this issue by proposing a relational kernel learning which can model relationship between sets of data and find shared structure among the time series datasets. We show the shared structure can help learning more accurate models for sets of regression problems with some synthetic data, US top market capitalization stock data and US house sales index data. -
dc.description.statementofresponsibility open -
dc.format.extent pdf -
dc.language ENG -
dc.publisher Graduate School of UNIST -
dc.subject Statistical Relational Learning -
dc.subject Gaussian Processes -
dc.subject Automatic Statistician -
dc.subject Automatic Bayesian Covariance Discovery -
dc.title The Automatic Statistician: A Relational Perspective -
dc.type Master's thesis -
dc.administration.regnum 000002237195 -
Appears in Collections:

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show simple item record


  • mendeley


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