论文标题
广泛的神经网络知情学习：收敛，概括和取样复杂性
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
论文作者
论文摘要
通过将域知识与标记的样本集成在一起，知情的机器学习已经出现，以提高广泛应用的学习绩效。尽管如此，对注射领域知识的作用的严格理解尚未探索。在本文中，我们考虑了一个知情的深度神经网络（DNN），并将过度参数化和域知识纳入其培训目标功能，并研究领域知识如何以及为什么会使绩效受益。具体而言，我们定量地证明了域知识在知情学习中的两个好处 - 正规化基于标签的监督并补充标记的样本 - 并揭示了人口风险的标签和知识不完美性之间的权衡。基于理论分析，我们提出了一个广义知情的培训目标，以更好地利用知识的益处，并平衡标签和知识不完美，这是由人口风险约束验证的。我们对抽样复杂性的分析阐明了如何选择超参数进行知情学习的灯光，并进一步证明了知识知情学习的优势。
By integrating domain knowledge with labeled samples, informed machine learning has been emerging to improve the learning performance for a wide range of applications. Nonetheless, rigorous understanding of the role of injected domain knowledge has been under-explored. In this paper, we consider an informed deep neural network (DNN) with over-parameterization and domain knowledge integrated into its training objective function, and study how and why domain knowledge benefits the performance. Concretely, we quantitatively demonstrate the two benefits of domain knowledge in informed learning - regularizing the label-based supervision and supplementing the labeled samples - and reveal the trade-off between label and knowledge imperfectness in the bound of the population risk. Based on the theoretical analysis, we propose a generalized informed training objective to better exploit the benefits of knowledge and balance the label and knowledge imperfectness, which is validated by the population risk bound. Our analysis on sampling complexity sheds lights on how to choose the hyper-parameters for informed learning, and further justifies the advantages of knowledge informed learning.
