logo Idiap Research Institute        
 [BibTeX] [Marc21]
Stability and Hypothesis Transfer Learning
Type of publication: Conference paper
Citation: Kuzborskij_ICML_2013
Publication status: Accepted
Booktitle: International Conference on Machine Learning
Year: 2013
Month: June
Abstract: We consider the transfer learning scenario, where the learner does not have access to the source domain directly, but rather operates on the basis of hypotheses induced from it - the Hypothesis Transfer Learning (HTL) problem. Particularly, we conduct a theoretical analysis of HTL by considering the algorithmic stability of a class of HTL algorithms based on Regularized Least Squares with biased regularization. We show that the relatedness of source and target domains accelerates the convergence of the Leave-One-Out error to the generalization error, thus enabling the use of the Leave-One-Out error to find the optimal transfer parameters, even in the presence of a small training set. In case of unrelated domains we also suggest a theoretically principled way to prevent negative transfer, so that in the limit we recover the performance of the algorithm not using any knowledge from the source domain.
Keywords: domain adaptation, learning theory, leave-one-out, regularized least squares, stability, transfer learning
Projects Idiap
Authors Kuzborskij, Ilja
Orabona, Francesco
Added by: [UNK]
Total mark: 0
  • Kuzborskij_ICML_2013.pdf