Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

12.5%25.0%37.5%50.0% · May 199319922001200920172026
48 results for kernel eigenvalues

The paper explores how kernel eigenalignments affect generalization in KRR.

problem Achieving robust generalization in kernel methods.
method Direct connection between generalization and matrix eigenvectors/eigenvalues, focusing on finite-sample settings.
result Strong generalization requires increasing eigenvector alignment, eigenvalue magnitude, or gaps between eigenvalues.

The paper develops heat kernel comparison theorems and applies them to spectral geometry.

problem Developing mathematical tools for spectral geometry.
method Established weighted heat kernel comparison theorems for manifolds with bounded radial curvatures.
result Two eigenvalue comparison theorems for the first Dirichlet eigenvalue of the Witten-Laplacian.

Paper calculates eigenvalue decay rates for neural network kernels on general domains.

problem Determining eigenvalue decay rates for neural network kernels on arbitrary domains.
method Proved dynamics of wide neural networks approximates NTK on general domains, used minimax optimality and interpolation spaces.
result Provided strategy to calculate eigenvalue decay rates for neural network kernels.

Study eigenvalue distributions of neural kernels for linear-width networks.

problem Eigenvalue distributions of neural kernels in linear-width networks.
method Asymptotic analysis of Conjugate Kernel and Neural Tangent Kernel under random initialization and approximate orthogonality.
result Eigenvalue distributions converge to deterministic limits, described by recursive fixed-point equations.

This paper is a tutorial for eigenvalue and generalized eigenvalue problems. We first introduce eigenvalue problem, eigen-decomposition (spectral decomposition), and generalized eigenvalue problem. Then, we mention the optimization problems which yield to the eigenvalue and generalized eigenvalue problems. We also prov…

2019-03-25abs ↗pdf ↗

Deep ReLU networks approximate as well as shallow ones in kernel regimes.

problem Understanding the limitations of kernel methods for deep ReLU networks.
method Characterizing eigenvalue decays of kernels derived from deep ReLU networks.
result Deep ReLU networks and shallow two-layer networks have equivalent approximation properties in kernel regimes.

In this paper we study the concentration properties for the eigenvalues of kernel matrices, which are central objects in a wide range of kernel methods and, more recently, in network analysis. We present a set of concentration inequalities tailored for each individual eigenvalue of the kernel matrix with respect to its…

2018-12-05abs ↗pdf ↗

Sharp Gaussian bounds derived for Schrödinger kernel on Ricci solitons.

problem Analyzing Schrödinger heat kernel on gradient shrinking Ricci solitons.
method Deriving sharp Gaussian upper bounds for the Schrödinger heat kernel.
result Sharp upper and lower bounds for eigenvalues of the Schrödinger operator.

This paper improves neural network generalization by dynamically learning kernel parameters.

problem Improving neural network generalization and adaptability.
method Diagonal adaptive kernel model that learns kernel eigenvalues and output coefficients during training.
result The diagonal adaptive kernel model significantly improves generalization over fixed-kernel methods.

Sigmoid autoencoders can implement associative memory with certain conditions.

problem Implementing associative memory in neural networks.
method Theoretical analysis of overparameterized sigmoid autoencoders using the NTK and iterative maps.
result Overparameterized sigmoid autoencoders can have attractors in the NTK limit, leading to associative memory.

Active data collection improves convergence rates in operator learning.

problem Improving convergence rates in operator learning with linear target and stochastic input.
method Active data collection strategies with mean-zero stochastic process and continuous covariance kernels.
result Achieves arbitrarily fast error convergence rates with eigenvalue decay of covariance kernels.

We analyze the eigenvalue distribution of a neural network's kernel under specific scaling.

problem Analyzing the eigenvalue distribution of the Neural Tangent Kernel (NTK) of a neural network.
method Asymptotic analysis of the NTK matrix under given scaling conditions.
result The eigenvalue distribution is described as a free multiplicative convolution of the Marchenko-Pastur distribution and a deterministic distribution.

Study gaps and clusters in eigenvalues of magnetic Laplacian on manifolds.

problem Understanding gaps and clusters in eigenvalues of magnetic Laplacian on manifolds.
method Analyzes high tensor powers of Hermitian line bundles with non degenerate curvature, proving Riemann-Roch numbers for eigenvalue clusters and describing spectral projectors.
result Clusters and gaps in eigenvalues are described by Riemann-Roch numbers and have pointwise kernel descriptions.

Study spectral properties of graph Laplacian for manifold data.

problem Understanding spectral properties of graph Laplacian for manifold data.
method Non-asymptotic error bounds on spectral properties of empirical graph Laplacian.
result Eigenvalues and eigenspaces of empirical graph Laplacian are close to Laplace-Beltrami operator of manifold.

Two adaptive kernel selection methods improve the accuracy of Kernelized Diffusion Maps.

problem Selecting an appropriate kernel for Kernelized Diffusion Maps.
method Two complementary approaches: variational outer loop and unsupervised cross-validation.
result Both methods improve the quality and stability of the recovered eigenfunctions.

High-dimensional kernel regression struggles due to rotational invariance.

problem Kernel ridge regression struggles in high dimensions due to rotational invariance.
method Analysis of kernel properties and their impact on high-dimensional data.
result Lower bound on generalization error for high-dimensional kernel regression.

Two new algorithms reduce online kernel regression's computational cost while maintaining optimal regret bounds.

problem Trade-off between regret and computational cost in online kernel regression.
method AOGD-ALD and NONS-ALD algorithms dynamically maintain nearly orthogonal basis to approximate kernel mapping and control approximate error.
result Achieves nearly optimal regret bounds at sublinear computational complexity.

The study bounds heat kernel for manifolds with specific curvature conditions.

problem Estimating heat kernel for manifolds with Bakry-Émery Ricci curvature.
method Gaussian upper bound for heat kernel, proving L^1-Liouville property, deriving eigenvalue bounds.
result Established Gaussian upper bound for heat kernel, derived eigenvalue bounds.

The paper proves spectral convergence rates for graph Laplacian to manifold Laplace-Beltrami operator.

problem Spectral convergence of graph Laplacian to manifold Laplace-Beltrami operator.
method Analysis of Dirichlet form convergence and construction of approximate eigenfunctions via manifold heat kernel.
result Proves spectral convergence rates for Gaussian kernelized graph Laplacian.

New bounds on NTK's smallest eigenvalue for arbitrary data without distributional assumptions.

problem Existing bounds on NTK's smallest eigenvalue require distributional assumptions and high-dimensional data.
method Novel application of the hemisphere transform.
result Bounds on NTK's smallest eigenvalue hold with high probability even for constant input dimension.

Kernel discriminant analysis uses nonlinear embeddings to improve classification.

problem Limited effectiveness of linear discriminant analysis in capturing nonlinear features.
method Study of nonlinear embeddings in kernel discriminant analysis using polynomial and Gaussian kernels, solving generalized eigenvalue problems.
result Polynomial and Gaussian discriminants capture class differences through population moments and randomized projections.

This paper tightens bounds on the smallest eigenvalue of NTK for deep ReLU networks.

problem Analyzing the smallest eigenvalue of Neural Tangent Kernel for deep ReLU networks.
method Analyzing various quantities of independent interest, including lower bounds on the smallest singular value of hidden feature matrices and upper bounds on the Lipschitz constant of input-output feature maps.
result Tight bounds on the smallest eigenvalue of NTK matrices for deep ReLU nets, both in the limiting case of infinite widths and for finite widths.

We present a new method which generalizes subspace learning based on eigenvalue and generalized eigenvalue problems. This method, Roweis Discriminant Analysis (RDA), is named after Sam Roweis to whom the field of subspace learning owes significantly. RDA is a family of infinite number of algorithms where Principal Comp…

2019-10-11abs ↗pdf ↗

The paper studies heat kernels on weighted Riemannian manifolds with curvature bounds.

problem Estimating heat kernels on weighted Riemannian manifolds with lower Ricci curvature bounds.
method Establishing parabolic Harnack inequalities, proving Gaussian bounds for heat kernels, and constructing Li-Yau-type gradient estimates.
result Gaussian upper and lower bounds for the heat kernel, Liouville theorem, uniqueness property, and eigenvalue bounds.

The paper improves eigenvalue estimates for manifolds with Ricci curvature conditions.

problem Eigenvalue estimates for manifolds with Ricci curvature conditions.
method Proves eigenvalue estimates using a Kato condition on the negative part of Ricci curvature.
result Optimal eigenvalue estimates for Zhong-Yang type and Cheng-type bounds.

Study bounds on kernel function entropy for finite measures.

problem Investigate bounds on the ε-entropy of kernel classes.
method Sharp upper and lower bounds for p in [1, +∞] derived from eigenvalue behavior and Mercer series convergence.
result Proves tighter bounds for general kernels compared to previous work.

We present in this work a new family of kernels to compare positive measures on arbitrary spaces $\Xcal$ endowed with a positive kernel κκ, which translates naturally into kernels between histograms or clouds of points. We first cover the case where $\Xcal$ is Euclidian, and focus on kernels which take into account th…

2009-09-07abs ↗pdf ↗