Timezone: »

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
Kwang-Sung Jun · Ashok Cutkosky · Francesco Orabona

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #242

In this paper we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS). We propose a new randomized algorithm that has optimal generalization error bounds with respect to the square loss, closing a long-standing gap between upper and lower bounds. Moreover, we show that our algorithm has faster finite-time and asymptotic rates on problems where the Bayes risk with respect to the square loss is small. We state our results using standard tools from the theory of least square regression in RKHSs, namely, the decay of the eigenvalues of the associated integral operator and the complexity of the optimal predictor measured through the integral operator.

Author Information

Kwang-Sung Jun (U of Arizona)
Ashok Cutkosky (Google Research)
Francesco Orabona (Boston University)

More from the Same Authors