Relative Error Embeddings for the Gaussian Kernel Distance
This provides theoretical bounds for kernel methods in machine learning, but it is incremental as it builds on existing random Fourier features work.
The paper tackles the problem of approximating the Gaussian kernel distance using random Fourier features, achieving a (1+ε)-relative error guarantee. It shows that O((1/ε²) log(n)) dimensions are sufficient and necessary for n data points, and O((d/ε²) log(M)) dimensions for points in ℝ^d with bounded diameter M.
A reproducing kernel can define an embedding of a data point into an infinite dimensional reproducing kernel Hilbert space (RKHS). The norm in this space describes a distance, which we call the kernel distance. The random Fourier features (of Rahimi and Recht) describe an oblivious approximate mapping into finite dimensional Euclidean space that behaves similar to the RKHS. We show in this paper that for the Gaussian kernel the Euclidean norm between these mapped to features has $(1+ε)$-relative error with respect to the kernel distance. When there are $n$ data points, we show that $O((1/ε^2) \log(n))$ dimensions of the approximate feature space are sufficient and necessary. Without a bound on $n$, but when the original points lie in $\mathbb{R}^d$ and have diameter bounded by $\mathcal{M}$, then we show that $O((d/ε^2) \log(\mathcal{M}))$ dimensions are sufficient, and that this many are required, up to $\log(1/ε)$ factors.