Name
Abstract | ||
|---|---|---|
In this paper we investigate multi-task learning in the context of Gaussian Pro- cesses (GP). We propose a model that learns a shared covariance function on input-dependent features and a "free-form" covariance matrix over tasks. This al- lows for good flexibility when modelling inter-task dependencies while avoiding the need for large amounts of data for training. We show that under the assump- tion of noise-free observations and a block design, predictions for a given task only depend on its target values and therefore a cancellation of inter-task trans- fer occurs. We evaluate the benefits of our model on two practical applications: a compiler performance prediction problem and an exam score prediction task. Additionally, we make use of GP approximations and properties of our model in order to provide scalability to large data sets. |
Year | Venue | Keywords |
|---|---|---|
2007 | NIPS | gaussian process,block design,covariance matrix,multi task learning,covariance function |
Field | DocType | Citations |
Covariance function,Data set,Computer science,Block design,Compiler,Artificial intelligence,Gaussian process,Covariance matrix,Performance prediction,Machine learning,Scalability | Conference | 246 |
PageRank | References | Authors |
11.37 | 13 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Edwin V. Bonilla | 1 | 1008 | 53.32 |
| Kian Ming Adam Chai | 2 | 417 | 22.18 |
| Christopher K. I. Williams | 3 | 6807 | 631.16 |