Data-driven paradigms are well-known and salient demands of future wireless communication. Empowered by big data and machine learning, next-generation data-driven communication systems will be intelligent with the characteristics of expressiveness, scalability, interpretability, and especially uncertainty modeling, which can confidently involve diversified latent demands and personalized services in the foreseeable future. In this paper, we review a promising family of nonparametric Bayesian machine learning methods, i.e., Gaussian processes (GPs), and their applications in wireless communication. Since GPs achieve the expressive and interpretable learning ability with uncertainty, it is particularly suitable for wireless communication. Moreover, it provides a natural framework for collaborating data and empirical models (DEM). Specifically, we first envision three-level motivations of data-driven wireless communication using GPs. Then, we present the background of the GPs in terms of covariance structure and model inference. The expressiveness of the GP model using various interpretable kernel designs is surveyed, namely, stationary, non-stationary, deep, and multi-task kernels. Furthermore, we review the distributed GPs with promising scalability, which is suitable for applications in wireless networks with a large number of distributed edge devices. Finally, we list representative solutions and promising techniques that adopt GPs in wireless communication systems.
翻译:数据驱动范式是众所周知的,也是未来无线通信的突出要求。通过大数据和机器学习,下一代数据驱动的通信系统将具有智能,具有清晰度、可伸缩性、可解释性、特别是不确定性模型的特性,这在可预见的未来可以有信心地涉及多种潜在需求和个性化服务。在本文件中,我们从可变结构和模型推断的角度来回顾一个前景良好的非对称贝耶斯机器学习方法大家庭,即高西亚进程(GPs)及其在无线通信中的应用。由于GPs实现了有不确定性的直观和可解释的学习能力,它尤其适合无线通信。此外,它为合作的数据和经验模型(DEM)提供了一个自然框架。具体地说,我们首先设想了数据驱动的无线通信在三个层次上的积极性。然后,我们从可变性结构和模型推断的角度介绍GPs的背景。GPs模型使用各种可解释的内涵设计,即固定性、非静止、深度和多型式的学习能力,尤其适合无线式通信。最后,我们用有希望的GPS、可移动式的应用程序列表,在可发送的大规模应用的网络中,然后用大型可推广的大型GPs。