3 Search Results for "Simon, Hans Ulrich"

Document
DOI: 10.4230/LIPIcs.STACS.2013.185
Unlabeled Data Does Provably Help

Authors: Malte Darnstädt, Hans Ulrich Simon, and Balázs Szörényi

Published in: LIPIcs, Volume 20, 30th International Symposium on Theoretical Aspects of Computer Science (STACS 2013)

Abstract
A fully supervised learner needs access to correctly labeled examples whereas a semi-supervised learner has access to examples part of which are labeled and part of which are not. The hope is that a large collection of unlabeled examples significantly reduces the need for labeled-ones. It is widely believed that this reduction of "label complexity" is marginal unless the hidden target concept and the domain distribution satisfy some "compatibility assumptions". There are some recent papers in support of this belief. In this paper, we revitalize the discussion by presenting a result that goes in the other direction. To this end, we consider the PAC-learning model in two settings: the (classical) fully supervised setting and the semi-supervised setting. We show that the "label-complexity gap"' between the semi-supervised and the fully supervised setting can become arbitrarily large for concept classes of infinite VC-dimension (or sequences of classes whose VC-dimensions are finite but become arbitrarily large). On the other hand, this gap is bounded by O(ln |C|) for each finite concept class C that contains the constant zero- and the constant one-function. A similar statement holds for all classes C of finite VC-dimension.
Cite as

Malte Darnstädt, Hans Ulrich Simon, and Balázs Szörényi. Unlabeled Data Does Provably Help. In 30th International Symposium on Theoretical Aspects of Computer Science (STACS 2013). Leibniz International Proceedings in Informatics (LIPIcs), Volume 20, pp. 185-196, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2013)

Copy BibTex To Clipboard

@InProceedings{darnstadt_et_al:LIPIcs.STACS.2013.185,
  author =	{Darnst\"{a}dt, Malte and Simon, Hans Ulrich and Sz\"{o}r\'{e}nyi, Bal\'{a}zs},
  title =	{{Unlabeled Data Does Provably Help}},
  booktitle =	{30th International Symposium on Theoretical Aspects of Computer Science (STACS 2013)},
  pages =	{185--196},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-50-7},
  ISSN =	{1868-8969},
  year =	{2013},
  volume =	{20},
  editor =	{Portier, Natacha and Wilke, Thomas},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.STACS.2013.185},
  URN =		{urn:nbn:de:0030-drops-39337},
  doi =		{10.4230/LIPIcs.STACS.2013.185},
  annote =	{Keywords: algorithmic learning, sample complexity, semi-supervised learning}
}
Document
DOI: 10.4230/DagSemRep.163
Theory and Practice of Machine Learning (Dagstuhl Seminar 9702)

Authors: Thomas G. Dietterich, Wolfgang Maass, Hans Ulrich Simon, and Robert S. Sutton

Published in: Dagstuhl Seminar Reports. Dagstuhl Seminar Reports, Volume 1 (2021)

Abstract
Cite as

Thomas G. Dietterich, Wolfgang Maass, Hans Ulrich Simon, and Robert S. Sutton. Theory and Practice of Machine Learning (Dagstuhl Seminar 9702). Dagstuhl Seminar Report 163, pp. 1-33, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (1997)

Copy BibTex To Clipboard

@TechReport{dietterich_et_al:DagSemRep.163,
  author =	{Dietterich, Thomas G. and Maass, Wolfgang and Simon, Hans Ulrich and Sutton, Robert S.},
  title =	{{Theory and Practice of Machine Learning (Dagstuhl Seminar 9702)}},
  pages =	{1--33},
  ISSN =	{1619-0203},
  year =	{1997},
  type = 	{Dagstuhl Seminar Report},
  number =	{163},
  institution =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemRep.163},
  URN =		{urn:nbn:de:0030-drops-150503},
  doi =		{10.4230/DagSemRep.163},
}
Document
DOI: 10.4230/DagSemRep.91
Theory and Praxis of Machine Learning (Dagstuhl Seminar 9426)

Authors: Thomas Dietterich, Wolfgang Maass, Hans-Ulrich Simon, and Manfred Warmuth

Published in: Dagstuhl Seminar Reports. Dagstuhl Seminar Reports, Volume 1 (2021)

Abstract
Cite as

Thomas Dietterich, Wolfgang Maass, Hans-Ulrich Simon, and Manfred Warmuth. Theory and Praxis of Machine Learning (Dagstuhl Seminar 9426). Dagstuhl Seminar Report 91, pp. 1-24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (1994)

Copy BibTex To Clipboard

@TechReport{dietterich_et_al:DagSemRep.91,
  author =	{Dietterich, Thomas and Maass, Wolfgang and Simon, Hans-Ulrich and Warmuth, Manfred},
  title =	{{Theory and Praxis of Machine Learning (Dagstuhl Seminar 9426)}},
  pages =	{1--24},
  ISSN =	{1619-0203},
  year =	{1994},
  type = 	{Dagstuhl Seminar Report},
  number =	{91},
  institution =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemRep.91},
  URN =		{urn:nbn:de:0030-drops-149796},
  doi =		{10.4230/DagSemRep.91},
}
  • Refine by Author
  • 2 Maass, Wolfgang
  • 2 Simon, Hans Ulrich
  • 1 Darnstädt, Malte
  • 1 Dietterich, Thomas
  • 1 Dietterich, Thomas G.
  • Show More...

  • Refine by Classification

  • Refine by Keyword
  • 1 algorithmic learning
  • 1 sample complexity
  • 1 semi-supervised learning

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 1 1994
  • 1 1997
  • 1 2013

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact