arXiv research

Graph kernels for metric graphs using tropical algebra.

Investigates O(n)-invariant metrics on SPD matrices, extending kernel metrics.

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

Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework. Specifically, we learn local metrics optimized from parametric generative models. T…

Study shows Bergman kernel quotient approaches one for punctured surfaces.

Kernel regression is a popular non-parametric fitting technique. It aims at learning a function which estimates the targets for test inputs as precise as possible. Generally, the function value for a test input is estimated by a weighted average of the surrounding training examples. The weights are typically computed b…

In this paper we consider a punctured Riemann surface endowed with a Hermitian metric which equals the Poincaré metric near the punctures and a holomorphic line bundle which polarizes the metric. We show that the Bergman kernel can be localized around the singularities and its local model is the Bergman kernel of the p…

Development of metrics for structural data-generating mechanisms is fundamental in machine learning and the related fields. In this paper, we give a general framework to construct metrics on random nonlinear dynamical systems, defined with the Perron-Frobenius operators in vector-valued reproducing kernel Hilbert space…

Metric learning for classification has been intensively studied over the last decade. The idea is to learn a metric space induced from a normed vector space on which data from different classes are well separated. Different measures of the separation thus lead to various designs of the objective function in the metric …

Study heat kernel on manifolds with fibred boundary metrics.

Study shows quantum behavior near infinity in metric asymptotics.

New findings show fixed-kernel discriminators are weaker than feature-learning ones.

The paper studies invariant weighted Bergman metrics on domains.

New kernels defined for various spaces, including measures.

Theory explains why neural nets better learn Calabi-Yau metrics.

Study Bergman kernel metrics on degenerating hyperelliptic surfaces.

A new method estimates multi-dimensional value distributions using Hilbert space embeddings.

New KQEs improve probability metrics without mean function constraints.

We consider the problem of metric learning for multi-view data and present a novel method for learning within-view as well as between-view metrics in vector-valued kernel spaces, as a way to capture multi-modal structure of the data. We formulate two convex optimization problems to jointly learn the metric and the clas…

We prove that a metric measure space equipped with a Dirichlet form admitting an Euclidean heat kernel is necessarily isometric to the Euclidean space. This helps us providing an alternative proof of Colding's celebrated almost rigidity volume theorem via a quantitative version of our main result. We also discuss the c…

Study equivalence of metrics on noncompact Kähler manifolds with Bergman kernel properties.

Unified theory for adaptive image convolutions using metric perspectives.

The geometric approach to diffeomorphic image registration known as "large deformation by diffeomorphic metric mapping" (LDDMM) is based on a left action of diffeomorphisms on images, and a right-invariant metric on a diffeomorphism group, usually defined using a reproducing kernel. We explore the use of left-invariant…

Study Bergman kernels on complex hyperbolic cusps, generalizing previous results.

Kernel-UCBVI algorithm balances exploration and exploitation in metric state-action spaces.

This paper reviews MDS, Sammon mapping, and Isomap, explaining their theory and applications.

Gaussian kernel fails on circle and related spaces.

A new distance metric compares probability distributions using kernel covariance operators.

New example of manifolds with monotonic heat kernels found.

A faster graph kernel using optical random features.

Kernel mean embeddings have recently attracted the attention of the machine learning community. They map measures $μ$ from some set $M$ to functions in a reproducing kernel Hilbert space (RKHS) with kernel $k$. The RKHS distance of two mapped measures is a semi-metric $d_k$ over $M$. We study three questions. (I) For a…

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…

Producing overlapping schemes is a major issue in clustering. Recent proposed overlapping methods relies on the search of an optimal covering and are based on different metrics, such as Euclidean distance and I-Divergence, used to measure closeness between observations. In this paper, we propose the use of another meas…

Estimates path-valued data using signature metrics and local kernels.

We consider rough metrics on smooth manifolds and corresponding Laplacians induced by such metrics. We demonstrate that globally continuous heat kernels exist and are Hölder continuous locally in space and time. This is done via local parabolic Harnack estimates for weak solutions of operators in divergence form with b…

New metrics improve probabilistic forecasting, especially for rare events.

Let $X$ be a compact hyperbolic Riemann surface equipped with the Poincaré metric. For any integer $k\geq 2$, we investigate the Bergman kernel associated to the holomorphic Hermitian line bundle $Ω^{\otimes k}_X$, where $Ø$ is the holomorphic cotangent bundle of $X$. Our first main result estimates the corresponding B…

Following Donaldson's oppenness theorem on deforming a conical Kähler-Einstein metric, we prove a parabolic Schauder-type estimate with respect to conical metrics. As a corollary, we show that the conical Kähler-Ricci Flow exists for short time. The key is to establish the relevant heat kernel estimates, where we use t…

Study proposes a new metric for comparing Gaussian mixtures in RKHS.

We study large-scale kernel methods for acoustic modeling in speech recognition and compare their performance to deep neural networks (DNNs). We perform experiments on four speech recognition datasets, including the TIMIT and Broadcast News benchmark tasks, and compare these two types of models on frame-level performan…

This study compares and evaluates categorical kernels for Gaussian process regression.

In this paper, we study the large time behavior of the heat kernel on complete Riemannian manifolds with nonnegative Ricci curvature, which was studied by P. Li with additional maximum volume growth assumption. Following Y. Ding's original strategy, by blowing down the metric, using Cheeger and Colding's theory about l…

KeRNS tackles non-stationary reinforcement learning in metric spaces.

In this paper, using the Greiner's approach to heat kernel asymptotics, we give new proofs of the equivariant Gauss-Bonnet-Chern formula and the variation formulas for the equivariant Ray-Singer metric, which are originally due to J. M. Bismut and W. Zhang.

New method for reducing dimensions of distributional data.

A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing, and independence testing. This embedding represents any probability measure as a mean element in a reproducing kernel Hilbert space (RKHS). A pseudometric on the spac…

New algorithm detects changes in Markov kernels with unknown post-change kernel.

ConCuR generates high-quality CUDA kernels with concise reasoning traces.