Extendedt-process regression models

Gaussian Process Regression with Mismatched Models

Learning curves for Gaussian process regression are well understood when the 'student' model happens to match the 'teacher' (true data generation process). I derive approximations to the learning curves for the more generic case of mismatched models, and find very rich behaviour: For large input space dimensionality, where the results become exact, there are universal (student-independent) plat...

Generalized Ridge Regression Estimator in Semiparametric Regression Models

In the context of ridge regression, the estimation of ridge (shrinkage) parameter plays an important role in analyzing data. Many efforts have been put to develop skills and methods of computing shrinkage estimators for different full-parametric ridge regression approaches, using eigenvalues. However, the estimation of shrinkage parameter is neglected for semiparametric regression models. The m...

Approximation of Gaussian process regression models after training

The evaluation of a standard Gaussian process regression model takes time linear in the number of training data points. In this paper, the models are approximated in the feature space after training. It is empirically shown that the time required for evaluation can be drastically reduced without considerable loss in performance.

Gaussian process models for robust regression, classification, and reinforcement learning

Training Gaussian Process Regression models using optimized trajectories

Quadrotor helicopters and robot manipulators are used widely for both research and industrial applications. Both quadrotors and manipulators are difficult to model. Quadrotors have complex dynamic models, especially at high speeds. Obtaining an accurate model of manipulator dynamics is often difficult, due to inaccurate values for link parameters and dynamics such as friction which are difficul...