On the Intrinsic Dimensions of Data in Kernel Learning

The manifold hypothesis suggests that the generalization performance of machine learning methods improves significantly when the intrinsic dimension of the input distribution's support is low. In the context of Kernel Ridge Regression (KRR), we investigate two alternative notions of intrinsic dimension. The first, denoted $d_\varrho$, is the upper Minkowski dimension defined with respect to the canonical metric induced by a kernel function $K$ on a domain $\Omega$. The second, denoted $d_K$, is the effective dimension, derived from the decay rate of Kolmogorov $n$-widths associated with $K$ on $\Omega$. Given a probability measure $\mu$ on $\Omega$, we analyze the relationship between these $n$-widths and eigenvalues of the integral operator $\phi \mapsto \int_\Omega K(\cdot,x)\phi(x)\,d\mu(x)$. We show that, for a fixed domain $\Omega$, the Kolmogorov $n$-widths characterize the worst-case eigenvalue decay across all probability measures $\mu$ supported on $\Omega$. These eigenvalues are central to understanding the generalization behavior of KRR, enabling us to derive an excess error bound of order $$ \mathcal{O}\left(n^{-\frac{2+d_K}{2+2d_K} + \varepsilon}\right) $$ for any $\varepsilon > 0$, when the training set size $n$ is large. We also propose an algorithm that estimates upper bounds on the $n$-widths using only a finite sample from $\mu$. For distributions close to uniform, we prove that $\varepsilon$-accurate upper bounds on all $n$-widths can be computed with high probability using at most $$ \mathcal{O}\left(\varepsilon^{-d_\varrho}\log\frac{1}{\varepsilon}\right) $$ samples, with fewer required for small $n$. Finally, we compute the effective dimension $d_K$ numerically for various fractal sets. Our results show that, for kernels such as the Laplace kernel, the effective dimension $d_K$ can be significantly smaller than the Minkowski dimension $d_\varrho$, even though $d_K = d_\varrho$ provably holds on regular domains.