Corpus ID: 5654590

Random Fourier Features For Operator-Valued Kernels

@article{Brault2016RandomFF,
  title={Random Fourier Features For Operator-Valued Kernels},
  author={Romain Brault and M. Heinonen and Florence d'Alch{\'e}-Buc},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.02536}
}
Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these methods, we extend the celebrated Random Fourier Feature methodology to get an approximation of operator-valued kernels. We propose a general principle for Operator-valued Random Fourier Feature construction relying on a generalization of Bochner's theorem for translation-invariant… Expand
17 Citations
Large-scale operator-valued kernel regression
Scaling up Vector Autoregressive Models With Operator-Valued Random Fourier Features
  • 1
  • PDF
Entangled Kernels - Beyond Separability
  • PDF
Entangled Kernels
  • 2
  • PDF
Periodic Kernel Approximation by Index Set Fourier Series Features
  • PDF
Denoising Score Matching with Random Fourier Features
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 36 REFERENCES
Online Learning with Multiple Operator-valued Kernels
  • 6
  • PDF
On Learning Vector-Valued Functions
  • 430
  • PDF
Refinement of Operator-valued Reproducing Kernels
  • 22
  • PDF
Kernels for Vector-Valued Functions: a Review
  • 417
  • PDF
Learning Output Kernels with Block Coordinate Descent
  • 75
  • PDF
On the Error of Random Fourier Features
  • 108
  • PDF
Scalable Matrix-valued Kernel Learning for High-dimensional Nonlinear Multivariate Regression and Granger Causality
  • 43
  • PDF
Optimal Rates for Random Fourier Features
  • 75
  • PDF
Matrix-valued kernels for shape deformation analysis
  • 31
  • PDF
Random Features for Large-Scale Kernel Machines
  • 2,269
  • Highly Influential
  • PDF
...
1
2
3
4
...