English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Measuring Learning Complexity with Criteria Epitomizers

Case, J., & Kötzing, T. (2011). Measuring Learning Complexity with Criteria Epitomizers. In T. Schwentick, & C. Dürr (Eds.), 28th International Symposium on Theoretical Aspects of Computer Science (pp. 320-331). Dagstuhl, Wadern: Leibniz-Zentrum für Informatik. doi:10.4230/LIPIcs.STACS.2011.320.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0010-124E-A Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-057C-F
Genre: Conference Paper

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Case, John1, Author
Kötzing, Timo2, Author           
Affiliations:
1External Organizations, ou_persistent22              
2Algorithms and Complexity, MPI for Informatics, Max Planck Society, ou_24019              

Content

show
hide
Free keywords: -
 Abstract: In prior papers, beginning with the seminal work by Freivalds et al. 1995, the notion of intrinsic complexity is used to analyze the learning complexity of sets of functions in a Gold-style learning setting. Herein are pointed out some weaknesses of this notion. Offered is an alternative based on epitomizing sets of functions -- sets, which are learnable under a given learning criterion, but not under other criteria which are not at least as powerful. To capture the idea of epitomizing sets, new reducibility notions are given based on robust learning (closure of learning under certain classes of operators). Various degrees of epitomizing sets are characterized as the sets complete with respect to corresponding reducibility notions! These characterizations also provide an easy method for showing sets to be epitomizers, and they are, then, employed to prove several sets to be epitomizing. Furthermore, a scheme is provided to generate easily very strong epitomizers for a multitude of learning criteria. These strong epitomizers are so-called self-learning sets, previously applied by Case & Koetzing, 2010. These strong epitomizers can be generated and employed in a myriad of settings to witness the strict separation in learning power between the criteria so epitomized and other not as powerful criteria!

Details

show
hide
Language(s): eng - English
 Dates: 20112011
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 618666
DOI: 10.4230/LIPIcs.STACS.2011.320
URI: http://drops.dagstuhl.de/opus/volltexte/2011/3023/
Other: Local-ID: C1256428004B93B8-3D09312563BAC08EC1257856005560F8-Cas-Koe:c:11:StacsEpit
 Degree: -

Event

show
hide
Title: 28th International Symposium on Theoretical Aspects of Computer Science
Place of Event: Dortmund, Germany
Start-/End Date: 2011-03-10 - 2011-03-12

Legal Case

show

Project information

show

Source 1

show
hide
Title: 28th International Symposium on Theoretical Aspects of Computer Science
  Abbreviation : STACS 2011
Source Genre: Proceedings
 Creator(s):
Schwentick, Thomas1, Editor
Dürr, Christoph1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Dagstuhl, Wadern : Leibniz-Zentrum für Informatik
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 320 - 331 Identifier: ISBN: 978-3-939897-25-5

Source 2

show
hide
Title: Leibniz International Proceedings in Informatics (LIPIcs)
  Alternative Title :
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -