Timezone: »

Towards a Unified Analysis of Random Fourier Features
Zhu Li · Jean-Francois Ton · Dino Oglic · Dino Sejdinovic

Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 101

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 between the computational cost and the expected risk convergence rate is problem specific and expressed in terms of the regularization parameter and the number of effective degrees of freedom. We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to ridge leverage scores and further reduces the required number of features. As ridge leverage scores are expensive to compute, we devise a simple approximation scheme which provably reduces the computational cost without loss of statistical efficiency.

Author Information

Zhu Li (University of Oxford)
Jean-Francois Ton (University of Oxford)
Dino Oglic (King's College London)
Dino Sejdinovic (University of Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors