arXiv research

Positive-definite kernel functions are fundamental elements of kernel methods and Gaussian processes. A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a probability distribution. Another construction, which appears to have attracted less…

Study characterizes kernel of mixed ray transform on simple surfaces.

Paper characterizes embeddability of function spaces into $L_p$-type RKBS via metric entropy.

Characterizes kernel interpolation in large dimensions, revealing optimal and sub-optimal regions.

Maps between non-compact surfaces can have geometric kernels under certain conditions.

Characterizes kernel of linearization for minimal surfaces problem

Characterizes neural kernel and NNGP for various activations.

Strictly proper kernel scores are well-known tool in probabilistic forecasting, while characteristic kernels have been extensively investigated in the machine learning literature. We first show that both notions coincide, so that insights from one part of the literature can be used in the other. We then show that the m…

Study uses robust signature moments to characterize laws of stochastic processes.

The X-ray transform on the periodic slab $[0,1]\times\mathbb T^n$, $n\geq0$, has a non-trivial kernel due to the symmetry of the manifold and presence of trapped geodesics. For tensor fields gauge freedom increases the kernel further, and the X-ray transform is not solenoidally injective unless $n=0$. We characterize t…

Determinantal point process have recently been used as models in machine learning and this has raised questions regarding the characterizations of conditional independence. In this paper we investigate characterizations of conditional independence. We describe some conditional independencies through the conditions on t…

We consider the asymptotic expansion of the heat kernel of a generalized Laplacian for $t\to 0^+$ and characterize the coefficients $a_k$ of this expansion by a natural intertwining property. In particular we will give a closed formula for the infinite order jet of these coefficients on the diagonal in terms of the loc…

Paper analyzes how contrastive learning structures learned representations.

Kernel k-Means algorithm improves clustering of non-linear data.

The paper uses Banach spaces to analyze neural networks.

Convolution and pooling improve kernel methods in image classification.

New algorithm improves dynamic mode decomposition for high-dimensional data.

Permutation-valued features arise in a variety of applications, either in a direct way when preferences are elicited over a collection of items, or an indirect way in which numerical ratings are converted to a ranking. To date, there has been relatively limited study of regression, classification, and testing problems …

Kernel PCA helps analyze multivariate extremes and clusters them effectively.

Transformers are explained as infinite-dimensional kernel machines.

The paper studies Lipschitz bounds for integral kernels under differentiability assumptions.

Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not well understood. In this paper we take steps toward filling this gap. Specifica…

Study RKHS on manifolds, linking Sobolev and diffusion spaces.

The study extends kernel universality to Riemannian symmetric spaces.

Study provides bounds for estimating intrinsic dimension using Gaussian kernels.

Kernel methods have been widely applied to machine learning and other questions of approximating an unknown function from its finite sample data. To ensure arbitrary accuracy of such approximation, various denseness conditions are imposed on the selected kernel. This note contributes to the study of universal, characte…

Approximating non-linear kernels using feature maps has gained a lot of interest in recent years due to applications in reducing training and testing times of SVM classifiers and other kernel based learning algorithms. We extend this line of work and present low distortion embeddings for dot product kernels into linear…

Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an a…

Paper proposes a simple estimator for DPP correlation kernels.

We explore the connection between Hilbertian metrics and positive definite kernels on the real line. In particular, we look at a well-known characterization of translation invariant Hilbertian metrics on the real line by von Neumann and Schoenberg (1941). Using this result we are able to give an alternate proof of Boch…

Study characterizes non-collapsed RCD(K, N) spaces using heat kernel metrics.

Functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting

The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their parts and sums over all pairs of parts. Assignment kernels, in contrast, are ob…

Study shows minimizing the norm of the ERM solution stabilizes kernel ridge-less regression.

We present a scalable Gaussian process model for identifying and characterizing smooth multidimensional changepoints, and automatically learning changes in expressive covariance structure. We use Random Kitchen Sink features to flexibly define a change surface in combination with expressive spectral mixture kernels to …

Paper develops a dual formulation for PCA in Hilbert spaces.

Deep neural networks define suitable reproducing kernel Banach spaces.

New differential operator helps characterize non-collapsed RCD spaces.

The paper analyzes the statistical cost of tuning kernel hyperparameters in robust regression.

Using the notion of equivariant Kirwan map, as defined by Goldin, we prove that -- in the case of Hamiltonian torus actions with isolated fixed points -- Tolman and Weitsman's description of the kernel of the Kirwan map can be deduced directly from the residue theorem of Jeffrey and Kirwan. A characterization of the ke…

Bayesian Complementary Kernelized Learning models complex spatiotemporal data.

We characterize the conjugate linearized Ricci flow and the associated backward heat kernel on closed three--manifolds of bounded geometry. We discuss their properties, and introduce the notion of Ricci flow conjugated constraint sets which characterizes a way of Ricci flow averaging metric dependent geometrical data. …

Kernel methods are successful approaches for different machine learning problems. This success is mainly rooted in using feature maps and kernel matrices. Some methods rely on the eigenvalues/eigenvectors of the kernel matrix, while for other methods the spectral information can be used to estimate the excess risk. An …

Neural networks with DAGs show linearity as width increases.

MKA incorporates manifold geometry into kernel alignment for more robust representation comparison.

Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RK…

Maximum mean discrepancy (MMD), also called energy distance or N-distance in statistics and Hilbert-Schmidt independence criterion (HSIC), specifically distance covariance in statistics, are among the most popular and successful approaches to quantify the difference and independence of random variables, respectively. T…

Graph kernels for metric graphs using tropical algebra.