Related papers: Gaussian kernel expansion with basis functions uniformly bounded in $\mathcal{L}

Gaussian kernel expansion with basis functions uniformly bounded in $\mathcal{L}_{\infty}$

URL: http://arxiv.org/abs/2410.01394v1
Date: Wed, 2 Oct 2024 10:10:30 GMT
Title: Gaussian kernel expansion with basis functions uniformly bounded in $\mathcal{L}_{\infty}$
Authors: Mauro Bisiacco, Gianluigi Pillonetto,
Abstract summary: Kernel expansions are a topic of considerable interest in machine learning. Recent work in the literature has derived some of these results by assuming uniformly bounded basis functions in $mathcalL_infty$. Our main result is the construction on $mathbbR2$ of a Gaussian kernel expansion with weights in $ell_p$ for any $p>1$.
Score: 0.6138671548064355
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Kernel expansions are a topic of considerable interest in machine learning, also because of their relation to the so-called feature maps introduced in machine learning. Properties of the associated basis functions and weights (corresponding to eigenfunctions and eigenvalues in the Mercer setting) give insight into for example the structure of the associated reproducing kernel Hilbert space, the goodness of approximation schemes, the convergence rates and generalization properties of kernel machines. Recent work in the literature has derived some of these results by assuming uniformly bounded basis functions in $\mathcal{L}_\infty$. Motivated by this line of research, we investigate under this constraint all possible kernel expansions of the Gaussian kernel, one of the most widely used models in machine learning. Our main result is the construction on $\mathbb{R}^2$ of a Gaussian kernel expansion with weights in $\ell_p$ for any $p>1$. This result is optimal since we also prove that $p=1$ cannot be reached by the Gaussian kernel, nor by any of the other radial basis function kernels commonly used in the literature. A consequence for this kind of kernels is also the non-existence of Mercer expansions on $\mathbb{R}^2$, with respect to any finite measure, whose eigenfunctions all belong to a closed ball of $\mathcal{L}_\infty$.

Related papers

Universality of kernel random matrices and kernel regression in the quadratic regime [18.51014786894174]
In this work, we extend the study of kernel kernel regression to the quadratic regime. We establish an operator norm approximation bound for the difference between the original kernel random matrix and a quadratic kernel random matrix. We characterize the precise training and generalization errors for KRR in the quadratic regime when $n/d2$ converges to a nonzero constant.
arXiv Detail & Related papers (2024-08-02T07:29:49Z)
A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing [68.80803866919123]
Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed $mathbfx*$ rather than for all $mathbfx*$ simultaneously. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index models as canonical examples. We also develop a concentration inequality that produces tighter bounds for product processes whose index sets have low metric entropy.
arXiv Detail & Related papers (2023-09-25T17:54:19Z)
Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
arXiv Detail & Related papers (2022-06-17T17:55:43Z)
Orthonormal Expansions for Translation-Invariant Kernels [8.646318875448644]
We derive explicit expansions on the real line for (i) Mat'ern kernels of all half-integer orders in terms of associated Laguerre functions, (ii) the Cauchy kernel in terms of rational functions, and (iii) the Gaussian kernel in terms of Hermite functions.
arXiv Detail & Related papers (2022-06-17T09:27:30Z)
An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings [21.727073594338297]
This study is motivated by applications in machine learning and statistics. We establish the weak limit of the empirical distribution of these random matrices in a scaling regime. Our results can be characterized as the free additive convolution between a Marchenko-Pastur law and a semicircle law.
arXiv Detail & Related papers (2022-05-12T18:50:21Z)
Spectral bounds of the $\varepsilon$-entropy of kernel classes [6.028247638616059]
We develop new bounds on the $varepsilon$-entropy of a unit ball in a reproducing kernel space induced by some Mercer kernel $K$. In our approach we exploit an ellipsoidal structure of a unit ball in RKHS and a previous work on covering numbers of an ellipsoid in the euclidean space.
arXiv Detail & Related papers (2022-04-09T16:45:22Z)
Random matrices in service of ML footprint: ternary random features with no performance loss [55.30329197651178]
We show that the eigenspectrum of $bf K$ is independent of the distribution of the i.i.d. entries of $bf w$. We propose a novel random technique, called Ternary Random Feature (TRF) The computation of the proposed random features requires no multiplication and a factor of $b$ less bits for storage compared to classical random features.
arXiv Detail & Related papers (2021-10-05T09:33:49Z)
Minimum complexity interpolation in random features models [16.823029377470366]
kernel methods are heavily affected by the curse of dimensionality. We show that learning with $mathcalF_p$ norms is tractable in an infinite-dimensional convex problem. We introduce a proof technique based on uniform concentration in the dual.
arXiv Detail & Related papers (2021-03-30T00:00:02Z)
High-Dimensional Gaussian Process Inference with Derivatives [90.8033626920884]
We show that in the low-data regime $ND$, the Gram matrix can be decomposed in a manner that reduces the cost of inference to $mathcalO(N2D + (N2)3)$. We demonstrate this potential in a variety of tasks relevant for machine learning, such as optimization and Hamiltonian Monte Carlo with predictive gradients.
arXiv Detail & Related papers (2021-02-15T13:24:41Z)
On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces [208.67848059021915]
We study the exploration-exploitation tradeoff at the core of reinforcement learning. In particular, we prove that the complexity of the function class $mathcalF$ characterizes the complexity of the function. Our regret bounds are independent of the number of episodes.
arXiv Detail & Related papers (2020-11-09T18:32:22Z)
Linear Time Sinkhorn Divergences using Positive Features [51.50788603386766]
Solving optimal transport with an entropic regularization requires computing a $ntimes n$ kernel matrix that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-logdotpvarphi(x)varphi(y)$ where $varphi$ is a map from the ground space onto the positive orthant $RRr_+$, with $rll n$.
arXiv Detail & Related papers (2020-06-12T10:21:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.