标题： 非线性多任务学习与深度高斯过程 显示英文标题

标题： Non-linear Multitask Learning with Deep Gaussian Processes

摘要： 我们提出了一个针对深度高斯过程（DGPs）的多任务学习公式，通过潜在过程的非线性混合实现。潜在空间由捕捉任务内信息的私有过程和捕捉跨任务依赖性的共享过程组成。我们提出了两种不同的方法来分割潜在空间：通过硬编码共享和任务特定过程，或者通过使用自动相关确定核的软共享。我们证明了我们的公式能够提高学习性能，并在任务之间传递信息，在真实世界和基准设置下优于其他概率多任务学习模型。 显示英文摘要

摘要： We present a multi-task learning formulation for Deep Gaussian processes (DGPs), through non-linear mixtures of latent processes. The latent space is composed of private processes that capture within-task information and shared processes that capture across-task dependencies. We propose two different methods for segmenting the latent space: through hard coding shared and task-specific processes or through soft sharing with Automatic Relevance Determination kernels. We show that our formulation is able to improve the learning performance and transfer information between the tasks, outperforming other probabilistic multi-task learning models across real-world and benchmarking settings.