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.

169,181 papers · 148 categories

Trend · papers per month

74149223297 · May 202619922001200920182026
48 results for smooth kernels

Upper bounds for Bergman kernels from smooth Kähler potentials.

problem Bounding Bergman kernels from smooth Kähler potentials.
method Using Taylor coefficients of the Kähler potential, we give upper bounds for Bergman kernels of tensor powers of a smooth positive line bundle.
result Improved off-diagonal rate of decay for analytic, quasi-analytic, and Gevrey potentials.

Generative models use kernel smoothing for conditioning on small example sets.

problem Improving generative models' performance with limited conditioning examples.
method Showed that cross-attention conditioning is equivalent to kernel smoothing, specifically a Nadaraya--Watson kernel smoother.
result The approach predicts and confirms three failure regimes for kernel-based conditioning.

New algorithms learn in complex decision-making problems with smooth transitions.

problem Learning in complex decision-making problems with smooth transitions.
method UCB and PSRL philosophies applied to episodic Markov decision processes with kernel approximation.
result Low regret learning achieved in continuous state and action spaces.

Smooth kernel regularizer improves deep neural networks' performance with less data.

problem Deep neural networks need large datasets for effective learning.
method Proposes a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights, learned from previous experience.
result The smooth kernel regularizer improves visual recognition models over an L2 regularization baseline.

The paper explores how approximation theory can improve understanding of smooth kernels in machine learning.

problem Understanding the inferential properties of smooth kernels in machine learning.
method Analysis of eigenvalue decay, properties of eigenfunctions/eigenvectors, and fitting capacity of kernels.
result Eigenvalues of kernel matrices show nearly exponential decay, highlighting the 'approximation beats concentration' phenomenon.

Gaussian kernel tests are optimal against smooth alternatives.

problem Understanding the statistical properties of nonparametric tests using Gaussian kernels.
method Analysis of Gaussian kernel-based goodness-of-fit, homogeneity, and independence tests.
result Gaussian kernel tests are minimax optimal against smooth alternatives in all three settings.

Smooth bundles with rough data maintain Hodge kernel isomorphism.

problem Maintaining Hodge kernel isomorphism for smooth bundles with non-smooth geometric data.
method Analyzing nilpotent differential operators and Hodge-Dirac-type operators under perturbations of geometric data.
result Kernels of Hodge-Dirac operators remain isomorphic under uniform perturbations of geometric data.

Paper addresses bias in kernel density estimation under minimal assumptions.

problem Kernel density estimation bias under minimal assumptions.
method Demonstrates the need for a balance between kernel decay and bandwidth eigenvalues, and rigorously derives bias bounds.
result Explicit constants and rigorous derivation of bias bounds under minimal assumptions.

New method improves optimization algorithms without Lipschitz smoothness.

problem Improving optimization algorithms in the absence of Lipschitz smoothness.
method Dual kernel conditioning (DKC) to provide dual Lipschitz continuity.
result First complexity bounds and iterate convergence for random reshuffling mirror descent.

The paper studies kernel smoothing and mean shift for directional data, deriving convergence rates and mode estimation.

problem Statistical and computational problems of kernel smoothing for directional data.
method Generalization of mean shift to directional data, derivation of convergence rates, and investigation of mode estimation.
result Statistical convergence rates of directional KDE and its derivatives, ascending property of directional mean shift, and mode estimation.

New kernel improves MMDs with theoretical guarantees for gradient flows.

problem Non-smoothness of negative distance kernel in MMDs.
method Smoothed 1D absolute value function followed by fractional integral transform.
result Improved theoretical guarantees for Wasserstein gradient flows.

Extends Tanimoto kernel to real-valued functions.

problem Measuring similarity between real-valued functions.
method Unified representation of real-valued functions via sets, derived general form of the kernel, explicit feature representation, and smooth approximation.
result General Tanimoto kernel for real-valued functions.

The paper explores the identifiability and interpretability of Gaussian process models using different kernel structures.

problem Identifiability and interpretability issues in Gaussian process models.
method The paper examines both single-output and multi-output Gaussian process models using additive and multiplicative mixtures of Matérn kernels.
result The smoothness of a mixture of Matérn kernels is determined by the least smooth component, and none of the mixing weights or parameters are identifiable.

Robust learning method combines kernel smoothing and robust optimization.

problem Certifying robustness against distribution shifts in machine learning models.
method Adapting integral operator using supremal convolution for robustness, leveraging optimal transport.
result The method provides theoretical guarantees for certified robustness and competitive performance.

The paper studies heat kernels on modified manifolds and bounds their properties.

problem Bounding heat kernels on modified Riemannian manifolds.
method Derives upper bounds and gradient estimates for the heat kernel of (M,ildeg)(M, ilde{g}).
result Establishes upper bounds and gradient estimates for the heat kernel of modified manifolds.

Improved kernel ridge regression for large datasets using weighted random binning.

problem Efficiently approximating kernel matrices for large-scale datasets.
method Introduced weighted random binning features for locality sensitive hashing.
result Weighted random binning features generate Gaussian processes of any desired smoothness.

Study shows quantum behavior near infinity in metric asymptotics.

problem Quantum behavior of metrics near infinity on quasi-projective manifolds.
method Analysis of Bergman kernel function near smooth divisor at infinity of Cheng-Yau metric.
result Quantum phenomenon observed for points very close to the divisor at infinity.

Paper analyzes subsampling for regression with low smoothness, achieving good rates with minimal regularization.

problem Regression with non-smooth target functions in misspecified kernel settings.
method Nyström subsampling approach under general source conditions, focusing on minimal regularization.
result Achieves good learning rates for a wide range of source conditions with one regularization parameter.

Method predicts crime hotspots with high resolution.

problem Forecasting sparse spatiotemporal events like crime.
method Combines RKHS methods with autoregressive smoothing kernels.
result Significantly outperforms baseline models for sparse events.

New algorithm optimizes Hölder smooth functions in RKHS with tighter regret bounds.

problem Optimizing Hölder smooth functions in RKHS with bounded norm.
method Proposes a new algorithm ( exttt{LP-GP-UCB}) using Local Polynomial (LP) estimators and multi-scale UCB.
result Derives high probability bounds on simple and cumulative regret, matching optimal performance for SE kernel and uniformly tighter bounds for Matérn kernels.

This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, p…

2017-02-28abs ↗pdf ↗

Paper provides GOT convergence guarantees for sub-gamma distributions and dependent samples.

problem Estimating GOT distance under general settings.
method Gaussian-smoothed optimal transport (GOT) framework, sub-gamma distributions, dependent samples, kernel MMD distances.
result Convergence guarantees for GOT distance under more general settings.

Kernel regression predicts graph signals in noisy environments.

problem Predicting smooth graph signals in the presence of sparse noise.
method Kernel regression with 1\ell_1-norm and 2\ell_2-norm optimization using IRLS.
result Efficacy demonstrated on real-world temperature data.

New method interpolates training data and is consistent for various data distributions.

problem Establishing generalization guarantees for ensemble methods in the interpolating regime.
method Developed manifold-Hilbert kernel for Riemannian manifolds and used it in ensemble classification.
result Consistent ensemble classification method for broad data distributions.