# Not-So-Random Features

arXiv: https://arxiv.org/abs/1710.10230 · HTML: https://mlsanity.com/paper/1710.10230/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2017.

## Built on by (most cited first, 5 of 5)

- [On Learning the Transformer Kernel](https://mlsanity.com/paper/2110.08323/) (2021)
- [Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks](https://mlsanity.com/paper/2201.04738/) (2022)
- [Quantum Adaptive Fourier Features for Neural Density Estimation](https://mlsanity.com/paper/2208.00564/) (2022)
- [Spectraformer: A Unified Random Feature Framework for Transformer](https://mlsanity.com/paper/2405.15310/) (2024)
- [MetaKernel: Learning Variational Random Features with Limited Labels](https://mlsanity.com/paper/2105.03781/) (2021)

## Abstract (arXiv)

We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels. Our method produces a sequence of feature maps, iteratively refining the SVM margin. We provide rigorous guarantees for optimality and generalization, interpreting our algorithm as online equilibrium-finding dynamics in a certain two-player min-max game. Evaluations on synthetic and real-world datasets demonstrate scalability and consistent improvements over related random features-based methods.