Distributed robust Gaussian Process regression

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Distributed robust Gaussian Process regression. / Mair, Sebastian; Brefeld, Ulf.
in: Knowledge and Information Systems, Jahrgang 55, Nr. 2, 01.05.2018, S. 415-435.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Mair S, Brefeld U. Distributed robust Gaussian Process regression. Knowledge and Information Systems. 2018 Mai 1;55(2):415-435. Epub 2017 Jul 19. doi: 10.1007/s10115-017-1084-7

Bibtex

@article{e7e0e3faacc7473b99d76b870a3b77d6,
title = "Distributed robust Gaussian Process regression",
abstract = "We study distributed and robust Gaussian Processes where robustness is introduced by a Gaussian Process prior on the function values combined with a Student-t likelihood. The posterior distribution is approximated by a Laplace Approximation, and together with concepts from Bayesian Committee Machines, we efficiently distribute the computations and render robust GPs on huge data sets feasible. We provide a detailed derivation and report on empirical results. Our findings on real and artificial data show that our approach outperforms existing baselines in the presence of outliers by using all available data.",
keywords = "Business informatics, Distributed computation, Gaussian process regression, Laplace Approximation, Robust regression, Student-t likelihood",
author = "Sebastian Mair and Ulf Brefeld",
year = "2018",
month = may,
day = "1",
doi = "10.1007/s10115-017-1084-7",
language = "English",
volume = "55",
pages = "415--435",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer London",
number = "2",

}

RIS

TY - JOUR

T1 - Distributed robust Gaussian Process regression

AU - Mair, Sebastian

AU - Brefeld, Ulf

PY - 2018/5/1

Y1 - 2018/5/1

N2 - We study distributed and robust Gaussian Processes where robustness is introduced by a Gaussian Process prior on the function values combined with a Student-t likelihood. The posterior distribution is approximated by a Laplace Approximation, and together with concepts from Bayesian Committee Machines, we efficiently distribute the computations and render robust GPs on huge data sets feasible. We provide a detailed derivation and report on empirical results. Our findings on real and artificial data show that our approach outperforms existing baselines in the presence of outliers by using all available data.

AB - We study distributed and robust Gaussian Processes where robustness is introduced by a Gaussian Process prior on the function values combined with a Student-t likelihood. The posterior distribution is approximated by a Laplace Approximation, and together with concepts from Bayesian Committee Machines, we efficiently distribute the computations and render robust GPs on huge data sets feasible. We provide a detailed derivation and report on empirical results. Our findings on real and artificial data show that our approach outperforms existing baselines in the presence of outliers by using all available data.

KW - Business informatics

KW - Distributed computation

KW - Gaussian process regression

KW - Laplace Approximation

KW - Robust regression

KW - Student-t likelihood

UR - http://www.scopus.com/inward/record.url?scp=85025086950&partnerID=8YFLogxK

U2 - 10.1007/s10115-017-1084-7

DO - 10.1007/s10115-017-1084-7

M3 - Journal articles

VL - 55

SP - 415

EP - 435

JO - Knowledge and Information Systems

JF - Knowledge and Information Systems

SN - 0219-1377

IS - 2

ER -

DOI

Zuletzt angesehen

Aktivitäten

  1. Technische Universität Lodz
  2. Workshop on Negotiation and Conflict Resolution at University of Amsterdam - UVA 2018
  3. Plenary Speaker at the 2021 4th IEEE International Conference on Information Communication and Signal Processing (ICICSP 2021)
  4. Sound is not the Score
  5. The link between in- and external rotation of the auditor and the quality of financial accounting and audit
  6. Apidologie (Zeitschrift)
  7. Barnboken (Zeitschrift)
  8. Why do we need the applicants’ perspective in selection procedures? An answer to Kevin Murphy
  9. Universität Zürich
  10. Personalising the impersonal: Interaction in public information messages across cultures (Universität Bayreuth, invited talk)
  11. Member of the selection committee for the COAL Prize Art & Environment 2011
  12. It’s all about engagement with texts – Empirical findings about promoting students’ reading comprehension by well-structured texts
  13. Co-determination Workshop Lüneburg 2010
  14. The bumpy road from investigation to knowledge
  15. Rational Design of Molecules by Life Cycle Engineering.
  16. How viable are institutional innovations for national long-term governance? Lessons from a comparative empirical analysis
  17. 'Can you play a new CD,please?' Speech act representation in EFL textbooks: An interlanguage pragmatic appraisal (Universität Gießen, invited talk)
  18. Tagung "Mathe für alle" 2012
  19. Different cultures, different communicative norms: Implications for content and language integrated learning (Lüneburg)
  20. Biological Oxidation of Iron with Various Oxidants.
  21. Panel session on “The grand challenges of the 21st century”
  22. Conceptualizing the Governance of Global Telecoupling
  23. Organization Studies (Fachzeitschrift)
  24. Zootechnologies. A Media History of Swarm Intelligence
  25. Organization Studies (Fachzeitschrift)
  26. Joint Conference Society for Industrial and Applied Mathematics - DSPDEs 2010
  27. Arlene Raven and the Feminist Studio Workshop