ICLR 2018poster28 citations
Not-So-Random Features
Brian Bullins, Cyril Zhang, Yi Zhang
Abstract
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.
kernel learningrandom featuresonline learning
BibTeX
@inproceedings{
bullins2018notsorandom,
title={Not-So-Random Features},
author={Brian Bullins and Cyril Zhang and Yi Zhang},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=Hk8XMWgRb},
}