Learning Rates for Multi-task Regularization Networks
This work addresses a theoretical gap in multi-task learning for researchers, but it is incremental as it extends existing single-task analysis to multi-task settings.
The paper tackles the lack of learning rate estimates for multi-task learning by providing a mathematical analysis based on vector-valued reproducing kernel Hilbert spaces, resulting in an explicit learning rate that depends on sample data and task count, revealing that generalization ability decreases as tasks increase.
Multi-task learning is an important trend of machine learning in facing the era of artificial intelligence and big data. Despite a large amount of researches on learning rate estimates of various single-task machine learning algorithms, there is little parallel work for multi-task learning. We present mathematical analysis on the learning rate estimate of multi-task learning based on the theory of vector-valued reproducing kernel Hilbert spaces and matrix-valued reproducing kernels. For the typical multi-task regularization networks, an explicit learning rate dependent both on the number of sample data and the number of tasks is obtained. It reveals that the generalization ability of multi-task learning algorithms is indeed affected as the number of tasks increases.