Variational Heteroscedastic Gaussian Process Regression

  title={Variational Heteroscedastic Gaussian Process Regression},
  author={Miguel L{\'a}zaro-Gredilla and Michalis K. Titsias},
Standard Gaussian processes (GPs) model observations’ noise as constant throughout input space. This is often a too restrictive assumption, but one that is needed for GP inference to be tractable. In this work we present a non-standard variational approximation that allows accurate inference in heteroscedastic GPs (i.e., under inputdependent noise conditions). Computational cost is roughly twice that of the standard GP, and also scales as O(n). Accuracy is verified by comparing with the golden… CONTINUE READING
Highly Influential
This paper has highly influenced 18 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 129 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 86 extracted citations

Variable risk control via stochastic optimization

I. J. Robotics Res. • 2013
View 11 Excerpts
Highly Influenced

A probabilistic data-driven model for planar pushing

2017 IEEE International Conference on Robotics and Automation (ICRA) • 2017
View 5 Excerpts
Highly Influenced

Chained Gaussian Processes

View 6 Excerpts
Highly Influenced

Expensive multiobjective optimization for robotics with consideration of heteroscedastic noise

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2014
View 5 Excerpts
Highly Influenced

Simulation-Extrapolation Gaussian Processes for Input Noise Modeling

2014 16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing • 2014
View 8 Excerpts
Highly Influenced

A review of deterministic approximate inference techniques for Bayesian machine learning

Neural Computing and Applications • 2013
View 4 Excerpts
Highly Influenced

129 Citations

Citations per Year
Semantic Scholar estimates that this publication has 129 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 16 references

Kernel Conditional Quantile Estimation via Reduction Revisited

2009 Ninth IEEE International Conference on Data Mining • 2009
View 5 Excerpts
Highly Influenced

Some aspects of the spline smoothing approach to non-parametric regression curve fitting

B. W. Silverman
Journal of the Royal Statistical Society, • 1985
View 3 Excerpts
Highly Influenced

Gaussian Processes for Machine Learning

Advanced Lectures on Machine Learning • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…