Corpus ID: 59523588

Towards a Unified Analysis of Random Fourier Features

@inproceedings{Li2019TowardsAU,
  title={Towards a Unified Analysis of Random Fourier Features},
  author={Z. Li and Jean-Francois Ton and Dino Oglic and D. Sejdinovic},
  booktitle={ICML},
  year={2019}
}
Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused on specific learning tasks and typically gives pessimistic bounds which are at odds with the empirical results. We tackle these problems and provide the first unified risk analysis of learning with random Fourier features using the squared error and Lipschitz continuous loss functions. In our bounds, the trade-off… Expand
38 Citations
Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features
  • Highly Influenced
  • PDF
Denoising Score Matching with Random Fourier Features
  • PDF
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
  • 6
  • Highly Influenced
  • PDF
A General Scoring Rule for Randomized Kernel Approximation with Application to Canonical Correlation Analysis
  • 3
  • PDF
No-Trick (Treat) Kernel Adaptive Filtering using Deterministic Features
  • 1
  • PDF
Generalizing Random Fourier Features via Generalized Measures
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 40 REFERENCES
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
  • 82
  • Highly Influential
  • PDF
On the Error of Random Fourier Features
  • 110
  • PDF
Optimal Rates for Random Fourier Features
  • 76
  • PDF
Fast Randomized Kernel Ridge Regression with Statistical Guarantees
  • 181
  • PDF
Fast Randomized Kernel Methods With Statistical Guarantees
  • 71
  • PDF
Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates
  • 197
  • PDF
Sharp analysis of low-rank kernel matrix approximations
  • F. Bach
  • Mathematics, Computer Science
  • COLT
  • 2013
  • 205
  • Highly Influential
  • PDF
Generalization Properties of Learning with Random Features
  • 159
  • PDF
Optimal Rates for the Regularized Least-Squares Algorithm
  • 465
  • PDF
...
1
2
3
4
...