Consistent Multitask Learning with Nonlinear Output Relations
This addresses the challenge of modeling nonlinear task dependencies in multitask learning, which is incremental as it extends linear methods to nonlinear cases.
The paper tackles the problem of multitask learning with nonlinear task relationships by proposing a novel algorithm that enforces a system of nonlinear equations on joint outputs, showing consistency and efficient implementation, with experimental results indicating potential improvements.
Key to multitask learning is exploiting relationships between different tasks to improve prediction performance. If the relations are linear, regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to satisfy. We show that the algorithm is consistent and can be efficiently implemented. Experimental results show the potential of the proposed method.