Distributed robust Gaussian Process regression

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

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.
Original languageEnglish
JournalKnowledge and Information Systems
Volume55
Issue number2
Pages (from-to)415-435
Number of pages21
ISSN0219-1377
DOIs
Publication statusPublished - 01.05.2018

    Research areas

  • Business informatics - Distributed computation, Gaussian process regression, Laplace Approximation, Robust regression, Student-t likelihood

Recently viewed

Publications

  1. Exploiting linear partial information for optimal use of forecasts. With an application to U.S. economic policy
  2. Eliciting Learner Perceptions of Web 2.0 Tasks through Mixed-Methods Classroom Research
  3. Constructs for Assessing Integrated Reports-Testing the Predictive Validity of a Taxonomy for Organization Size, Industry, and Performance
  4. Simulation based comparison of safety-stock calculation methods
  5. Q-Adaptive Control of the nonlinear dynamics of the cantilever-sample system of an Atomic Force Microscope
  6. Selecting and Adapting Methods for Analysis and Design in Value-Sensitive Digital Social Innovation Projects: Toward Design Principles
  7. The effects of different on-line adaptive response time limits on speed and amount of learning in computer assisted instruction and intelligent tutoring
  8. Topic Embeddings – A New Approach to Classify Very Short Documents Based on Predefined Topics
  9. On robustness properties in permanent magnet machine control by using decoupling controller
  10. Integrating the underlying structure of stochasticity into community ecology
  11. Globally asymptotic output feedback tracking of robot manipulators with actuator constraints
  12. Mathematical relation between extended connectivity and eigenvector coefficients.
  13. Should learners use their hands for learning? Results from an eye-tracking study
  14. »HOW TO MAKE YOUR OWN SAMPLES«
  15. Harvesting information from captions for weakly supervised semantic segmentation
  16. Fast, Fully Automated Analysis of Voriconazole from Serum by LC-LC-ESI-MS-MS with Parallel Column-Switching Technique
  17. Analysis And Comparison Of Dispatching RuleBased Scheduling In Dual-Resource Constrained Shop-Floor Scenarios
  18. Closed-form Solution for the Direct Kinematics Problem of the Planar 3-RPR Parallel Mechanism
  19. Exploration strategies, performance, and error consequences when learning a complex computer task
  20. Lessons learned for spatial modelling of ecosystem services in support of ecosystem accounting
  21. Construct Objectification and De-Objectification in Organization Theory
  22. Holistic and scalable ranking of RDF data
  23. Lyapunov Convergence Analysis for Asymptotic Tracking Using Forward and Backward Euler Approximation of Discrete Differential Equations
  24. Contextual movement models based on normalizing flows
  25. Global Finite-Time Stabilization of Planar Linear Systems With Actuator Saturation
  26. Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention
  27. Web-scale extension of RDF knowledge bases from templated websites
  28. Clause identification using entropy guided transformation learning
  29. Experimentally established correlation of friction surfacing process temperature and deposit geometry
  30. Interpreting Strings, Weaving Threads