Learning across domains and tasks: theory meets practice

The main objective of the workshop is to document and discuss the recent rise of new research questions on the general problem of learning across domains and tasks, and the related topics of domain adaptation, multi-task, transfer learning, and dataset-bias. In the last years there has been an increasing boost of activity in these areas, many of them driven by practical applications, such as object categorization. Different solutions were studied for each of the listed topics mainly separately and without a joint theoretical framework. On the other hand, most of the the existing theoretical formulations model regimes that are rarely used in practice (e.g. adaptive methods that store all the source samples). The workshop will focus on closing this gap by providing an opportunity for theoreticians and practitioners to get together in one place to share and debate over current theories and empirical results.

Event dates: 10th of December 2013

The workshop will incorporate four invited talks by S. Ben-David, M. Pontil, T. Darrell, K. Grauman, all of them already confirmed their presence. We will call for extended abstracts on the topics of interest. Preference will be given to proposals which are likely to generate new debate or suggesting directions for future work. All the contributions will be presented through short talks and poster sessions.