Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
This provides theoretical insights for researchers in machine learning on integrating domain knowledge, though it is incremental as it builds on existing informed learning frameworks.
The paper tackles the problem of understanding how domain knowledge improves learning in over-parameterized deep neural networks, showing that it regularizes supervision and supplements labeled samples, with theoretical bounds on population risk and sampling complexity.
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.