Multi-stage Multi-task feature learning via adaptive threshold

A fundamental limitation of the common machine learning methods is the cost incurred by the preparation of the large training samples required for good generalization. Multi-task learning (MTL) offers a potential remedy. Unlike common single task learning, MTL accomplishes tasks simultaneously with other related tasks, using a shared representation. One general assumption of multi-task learning is that all tasks should share some common structures, including a similarity metric matrix [3], a low ranksubspace [4, 5], parametersofBayesianmodels [6] oracommon set of features [7, 8, 9]. Improved generalization is achieved because what is learned from each task can help with the learning of other tasks [10]. MTL has been successfully applied to many applications such as stock selection [3], speech classification [11] and medical diagnoses [12]. While the majority of existing multi-task feature learning algorithms assume that the relevant features are shared by all tasks, some studies have begun to consider a more general case where features can be commonly shared only among most, but not necessarily all of them. In other word, they try to learn the features specific to each task as well as the common features shared among tasks [1]. In addition, MTL is commonly formulated as a convex regularization problem.