Efficient tuning in supervised machine learning

Leiden Repository

Efficient tuning in supervised machine learning

Title: Efficient tuning in supervised machine learning
Author: Koch, Patrick
Publisher: Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University
Issue Date: 2013-10-29
Keywords: Machine learning
Parameter tuning
Model-assisted optimization
Sequential parameter optimization
Abstract: The tuning of learning algorithm parameters has become more and more important during the last years. With the fast growth of computational power and available memory databases have grown dramatically. This is very challenging for the tuning of parameters arising in machine learning, since the training can become very time-consuming for large datasets. For this reason efficient tuning methods are required, which are able to improve the predictions of the learning algorithms. In this thesis we incorporate model-assisted optimization techniques, for performing efficient optimization on noisy datasets with very limited budgets. Under this umbrella we also combine learning algorithms with methods for feature construction and selection. We propose to integrate a variety of elements into the learning process. E.g., can tuning be helpful in learning tasks like time series regression using state-of-the-art machine learning algorithms? Are statistical methods capable to reduce noise e ffects? Can surrogate models like Kriging learn a reasonable mapping of the parameter landscape to the quality measures, or are they deteriorated by disturbing factors? Summarizing all these parts, we analyze if superior learning algorithms can be created, with a special focus on efficient runtimes. Besides the advantages of systematic tuning approaches, we also highlight possible obstacles and issues of tuning. Di fferent tuning methods are compared and the impact of their features are exposed. It is a goal of this work to give users insights into applying state-of-the-art learning algorithms profitably in practice
Description: Promotores: T.H.W. Bäck, W. Konen
With summary in Dutch
Faculty: Faculteit der Wiskunde en Natuurwetenschappen
Citation: Koch, P., 2013, Doctoral thesis, Leiden University
ISBN: 9789451918925
Sponsor: Bundesministerium f ür Bildung und Forschung (Germany), Cologne University of Applied Sciences (Germany), Kind-Steinm uller-Stiftung (Gummersbach, Germany)
Handle: http://hdl.handle.net/1887/22055

Files in this item

Description Size View
application/pdf Full text 3.557Mb View/Open
application/pdf Cover 682.7Kb View/Open
application/pdf Title page_Contents 207.6Kb View/Open
application/pdf Chapter 1 Introduction 186.9Kb View/Open
application/pdf Chapter 2 1.148Mb View/Open
application/pdf Chapter 3 1.364Mb View/Open
application/pdf Chapter 4 585.5Kb View/Open
application/pdf Chapter 5 428.6Kb View/Open
application/pdf Chapter 6 934.3Kb View/Open
application/pdf Chapter 7 590.4Kb View/Open
application/pdf Chapter 8 Summary 240.2Kb View/Open
application/pdf Bibliography 246.2Kb View/Open
application/pdf Appendix A 379.4Kb View/Open
application/pdf Summary in Dutch 164.9Kb View/Open
application/pdf Curriculum Vitae 211.4Kb View/Open
application/pdf Propositions 157.9Kb View/Open

This item appears in the following Collection(s)