Skip to yearly menu bar Skip to main content


NeuralEF: Deconstructing Kernels by Deep Neural Networks

Zhijie Deng · Jiaxin Shi · Jun Zhu

Hall E #416

Keywords: [ PM: Spectral Methods ] [ Deep Learning ] [ MISC: Representation Learning ] [ Probabilistic Methods ] [ MISC: Kernel methods ] [ DL: Other Representation Learning ]


Learning the principal eigenfunctions of an integral operator defined by a kernel and a data distribution is at the core of many machine learning problems. Traditional nonparametric solutions based on the Nystrom formula suffer from scalability issues. Recent work has resorted to a parametric approach, i.e., training neural networks to approximate the eigenfunctions. However, the existing method relies on an expensive orthogonalization step and is difficult to implement. We show that these problems can be fixed by using a new series of objective functions that generalizes the EigenGame to function space. We test our method on a variety of supervised and unsupervised learning problems and show it provides accurate approximations to the eigenfunctions of polynomial, radial basis, neural network Gaussian process, and neural tangent kernels. Finally, we demonstrate our method can scale up linearised Laplace approximation of deep neural networks to modern image classification datasets through approximating the Gauss-Newton matrix. Code is available at

Chat is not available.