Joey Faulkner - September 7, 2016
Abstract
We propose a model that learns a shared covariance function on input-dependent features and a “free-form” covariance matrix over tasks. This allows for good flexibility when modelling inter-task dependencies while avoiding the need for large amounts of data for training'.
This seems like the canonical paper, I'm also going to look at a results one too which claims that :Surprisingly, multi-task learning can be asymptotically essentially useless, in the sense that examples from other tasks help only when the degree of inter-task correlation, ρ, is near its maximal value ρ = 1.
papers
code
Whiteboard notes