Timezone: »
Poster
Generalization Errors and Learning Curves for Regression with Multi-task Gaussian Processes
Kian Ming A Chai
We provide some insights into how task correlations in multi-task Gaussian process (GP) regression affect the generalization error and the learning curve. We analyze the asymmetric two-task case, where a secondary task is to help the learning of a primary task. Within this setting, we give bounds on the generalization error and the learning curve of the primary task. Our approach admits intuitive understandings of the multi-task GP by relating it to single-task GPs. For the case of one-dimensional input-space under optimal sampling with data only for the secondary task, the limitations of multi-task GP can be quantified explicitly.
Author Information
Kian Ming A Chai (University of Edinburgh)
More from the Same Authors
-
2008 Poster: Multi-task Gaussian Process Learning of Robot Inverse Dynamics »
Kian Ming A Chai · Chris Williams · Stefan Klanke · Sethu Vijayakumar -
2008 Spotlight: Multi-task Gaussian Process Learning of Robot Inverse Dynamics »
Kian Ming A Chai · Chris Williams · Stefan Klanke · Sethu Vijayakumar -
2007 Poster: Multi-task Gaussian Process Prediction »
Edwin Bonilla · Kian Ming A Chai · Chris Williams -
2007 Spotlight: Multi-task Gaussian Process Prediction »
Edwin Bonilla · Kian Ming A Chai · Chris Williams