Machine Learning, Optimization, and Anti-Training with Sacrificial Data

Persistent Link:
http://hdl.handle.net/10150/605111
Title:
Machine Learning, Optimization, and Anti-Training with Sacrificial Data
Author:
Valenzuela, Michael Lawrence
Issue Date:
2016
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
Traditionally the machine learning community has viewed the No Free Lunch (NFL) theorems for search and optimization as a limitation. I review, analyze, and unify the NFL theorem with the many frameworks to arrive at necessary conditions for improving black-box optimization, model selection, and machine learning in general. I review meta-learning literature to determine when and how meta-learning can benefit machine learning. We generalize meta-learning, in context of the NFL theorems, to arrive at a novel technique called Anti-Training with Sacrificial Data (ATSD). My technique applies at the meta level to arrive at domain specific algorithms and models. I also show how to generate sacrificial data. An extensive case study is presented along with simulated annealing results to demonstrate the efficacy of the ATSD method.
Type:
text; Electronic Dissertation
Keywords:
Machine Learning; Meta Optimization; No Free Lunch; Optimization; Sacrificial Data; Electrical & Computer Engineering; Anti-Training
Degree Name:
Ph.D.
Degree Level:
doctoral
Degree Program:
Graduate College; Electrical & Computer Engineering
Degree Grantor:
University of Arizona
Advisor:
Rozenbilt, Jerzy W.; Head, Kenneth L.

Full metadata record

DC FieldValue Language
dc.language.isoen_USen
dc.titleMachine Learning, Optimization, and Anti-Training with Sacrificial Dataen_US
dc.creatorValenzuela, Michael Lawrenceen
dc.contributor.authorValenzuela, Michael Lawrenceen
dc.date.issued2016en
dc.publisherThe University of Arizona.en
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en
dc.description.abstractTraditionally the machine learning community has viewed the No Free Lunch (NFL) theorems for search and optimization as a limitation. I review, analyze, and unify the NFL theorem with the many frameworks to arrive at necessary conditions for improving black-box optimization, model selection, and machine learning in general. I review meta-learning literature to determine when and how meta-learning can benefit machine learning. We generalize meta-learning, in context of the NFL theorems, to arrive at a novel technique called Anti-Training with Sacrificial Data (ATSD). My technique applies at the meta level to arrive at domain specific algorithms and models. I also show how to generate sacrificial data. An extensive case study is presented along with simulated annealing results to demonstrate the efficacy of the ATSD method.en
dc.typetexten
dc.typeElectronic Dissertationen
dc.subjectMachine Learningen
dc.subjectMeta Optimizationen
dc.subjectNo Free Lunchen
dc.subjectOptimizationen
dc.subjectSacrificial Dataen
dc.subjectElectrical & Computer Engineeringen
dc.subjectAnti-Trainingen
thesis.degree.namePh.D.en
thesis.degree.leveldoctoralen
thesis.degree.disciplineGraduate Collegeen
thesis.degree.disciplineElectrical & Computer Engineeringen
thesis.degree.grantorUniversity of Arizonaen
dc.contributor.advisorRozenbilt, Jerzy W.en
dc.contributor.advisorHead, Kenneth L.en
dc.contributor.committeememberRozenbilt, Jerzy W.en
dc.contributor.committeememberHead, Kenneth L.en
dc.contributor.committeememberLysecky, Roman L.en
dc.contributor.committeememberMarcellin, Michael W.en
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.