Andreas Maurer am@andreas-maurer.eu Adalbertstrasse 55 ; D-80799 ; Munchen ; Germany ; Department of Computer Science ; Centre for Computational Statistics ; Machine Learning ; Department of Computer Science ; UCL Interactive Centre
We investigate the use of sparse coding and dictionary learning in the context of multi task and transfer learning. The central as sumption of our learning method is that the tasks parameters are well approximated by sparse linear combinations of the atoms of a dictionary on a high or infinite dimensional space. This assumption, together with the large quantity of available data in the multi task and transfer learning settings, allows a principled choice of the dictionary. We pro vide bounds on the generalization error of this approach, for both settings. Numerical experiments on one synthetic and two real datasets show the advantage of our method over single task learning, a previous method based on orthogonal and dense representa tion of the tasks and a related method learn