Kuzborskij, IljaOrabona, Francesco2016-12-192016-12-192016-12-19201610.1007/s10994-016-5594-4https://infoscience.epfl.ch/handle/20.500.14299/132088In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can be instantiated with any non-negative smooth loss function and any strongly convex regularizer. We establish generalization and excess risk bounds, showing that, if the algorithm is fed with a good combination of source hypotheses, generalization happens at the fast rate O(1/m) instead of the usual O(1/sqrt(m)). On the other hand, if the source hypotheses combination is a misfit for the target task, we recover the usual learning rate. As a byproduct of our study, we also prove a new bound on the Rademacher complexity of the smooth loss class under weaker assumptions compared to previous works.text::journal::journal article::research article