Large-Scale Learning with Fourier Features and Tensor Decompositions

Abstract

Random Fourier features provide a way to tackle large-scale machine learning problems with kernel methods. Their slow Monte Carlo convergence rate has motivated the research of deterministic Fourier features whose approximation error can decrease exponentially in the number of basis functions. However, due to their tensor product extension to multiple dimensions, these methods suffer heavily from the curse of dimensionality, limiting their applicability to one, two or three-dimensional scenarios. In our approach we overcome said curse of dimensionality by exploiting the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. We derive a monotonically converging block coordinate descent algorithm with linear complexity in both the sample size and the dimensionality of the inputs for a regularized squared loss function, allowing to learn a parsimonious model in decomposed form using deterministic Fourier features. We demonstrate by means of numerical experiments how our low-rank tensor approach obtains the same performance of the corresponding nonparametric model, consistently outperforming random Fourier features.

arXiv comment9 pages, 6 figures. Reviewed version after peer-review. To be published in the proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)

References in corpus (11)

• Scikit-learn: Machine Learning in Python
• Tensor Decomposition for Signal Processing and Machine Learning
• Deep Neural Networks as Gaussian Processes
• Gaussian Processes for Big Data
• Scalable Variational Gaussian Process Classification
• Additive Gaussian Processes
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
• Compressing Recurrent Neural Network with Tensor Train
• Variational Fourier features for Gaussian processes
• Sparse Gaussian Processes with Spherical Harmonic Features
• Gauss-Legendre Features for Gaussian Process Regression