Despite their many desirable properties, Gaussian processes (GPs) are often compared unfavorably to deep neural networks (NNs) for lacking the ability to learn representations. Recent efforts to bridge the gap between GPs and deep NNs have yielded a new class of inter-domain variational GPs in which the inducing variables correspond to hidden units of a feedforward NN. In this work, we examine some practical issues associated with this approach and propose an extension that leverages the orthogonal decomposition of GPs to mitigate these limitations. In particular, we introduce spherical inter-domain features to construct more flexible data-dependent basis functions for both the principal and orthogonal components of the GP approximation and show that incorporating NN activation features under this framework not only alleviates these shortcomings but is more scalable than alternative strategies. Experiments on multiple benchmark datasets demonstrate the effectiveness of our approach.

翻译：尽管高斯过程（GPs）具有诸多理想特性，但常因缺乏表示学习能力而被认为不如深度神经网络（NNs）。近期弥合GP与深度NN之间差距的研究催生了一类新的跨域变分GP，其诱导变量对应于前馈NN的隐藏单元。本文探讨了该方法相关的若干实践问题，并提出一种利用GP正交分解来缓解这些局限性的扩展方案。具体而言，我们引入球形跨域特征为GP近似的正交分量与主分量构建更灵活的数据相关基函数，并证明在此框架下融入NN激活特征不仅能弥补上述不足，且比替代策略更具可扩展性。在多个基准数据集上的实验验证了该方法的有效性。