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.

168,695 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Feb 199419922001200920172026
48 results for finite kernel

Empirical study compares wide neural networks to kernel methods, resolving open questions.

problem Understanding the relationship between wide neural networks and kernel methods.
method Large-scale empirical study using various neural network architectures and kernel methods.
result Wide neural networks outperform fully-connected finite-width networks in some cases, but underperform convolutional finite-width networks.

The Bergman-Szegő kernel is analyzed for weakly pseudoconvex CR manifolds of finite type.

problem Analyzing the Bergman-Szegő kernel for specific CR manifolds.
method Constructing a parametrix for the Szegő kernel, extending earlier results.
result Extending Fefferman's boundary asymptotics to weakly pseudoconvex domains in \(\mathbb{C}^{2}\).

We show in this note that the Sobolev Discrepancy introduced in Mroueh et al in the context of generative adversarial networks, is actually the weighted negative Sobolev norm .H˙1(νq)||.||_{\dot{H}^{-1}(ν_q)}, that is known to linearize the Wasserstein W2W_2 distance and plays a fundamental role in the dynamic formulation of…

2018-05-16abs ↗pdf ↗

The study shows algebraic Bergman kernels imply finite type boundaries in complex domains.

problem Understanding the relationship between algebraic Bergman kernels and the finite type of boundaries in complex domains.
method Analyzing algebraic Bergman kernels and their implications on the finite type of boundaries in smoothly bounded pseudoconvex domains in C2\mathbb{C}^2.
result The boundary of a smoothly bounded pseudoconvex domain with an algebraic Bergman kernel of degree dd is of finite type with type r2dr \leq 2d.

Study on fluctuations in neural network kernels and predictions, focusing on finite width effects.

problem Characterizing fluctuations in finite width neural networks.
method Dynamical mean field theory analysis of wide but finite feature learning neural networks.
result Fluctuations in kernels and predictions are dynamically coupled, leading to reduced variance in feature learning regimes.

Study shows Bergman kernels match averages on quotient spaces, proving non-vanishing of Poincaré series.

problem Proving non-vanishing of Poincaré series on finite-volume quotients of Hermitian symmetric spaces.
method Using Bergman kernels and averaging over discrete groups, proving non-vanishing of Poincaré series.
result Large class of relative Poincaré series does not vanish on general locally symmetric spaces of finite volume.

A Hilbert space embedding for probability measures has recently been proposed, wherein any probability measure is represented as a mean element in a reproducing kernel Hilbert space (RKHS). Such an embedding has found applications in homogeneity testing, independence testing, dimensionality reduction, etc., with the re…

2010-03-03abs ↗pdf ↗

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

problem Exploration-exploitation dilemma in finite-horizon reinforcement learning with metric state-action spaces.
method Kernel-UCBVI, leveraging smoothness and kernel estimators of rewards and transitions.
result First regret bound for kernel-based RL using smoothing kernels, O(H3K2d/(2d+1))O(H^3 K^{2d/(2d+1)}).

Paper provides unbiased spectral moment estimates from finite data.

problem Challenges in estimating spectral moments from limited data.
method Dynamic programming approach to estimate spectral moments of kernel integral operator.
result Demonstrates consistency with theoretical spectra and practical utility in neural networks.

Uniform-in-time analysis for Stein Variational Gradient Descent across various metrics.

problem Understanding long-term behavior of finite-particle systems in relation to their mean-field limits.
method Developed uniform-in-time propagation-of-chaos results for continuous-time SVGD using cutoff strategies and finite-dimensional theories.
result Uniform-in-time propagation-of-chaos bounds in various metrics, including Langevin kernel Stein discrepancy, Wasserstein-1, and Wasserstein-2 distances.

Novel Newton method for large-scale kernel methods using random features.

problem Efficiently solving large-scale finite-sum minimization problems in RKHS.
method Randomized feature-based Newton method for empirical risk minimization.
result Local superlinear and global linear convergence of the method.

Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.

problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.

We examine groups whose resonance varieties, characteristic varieties and Sigma-invariants have a natural arithmetic group symmetry, and we explore implications on various finiteness properties of subgroups. We compute resonance varieties, characteristic varieties and Alexander polynomials of Torelli groups, and we sho…

2010-02-03abs ↗pdf ↗

The paper analyzes rates for a modified gradient descent method using Stein variational gradients.

problem Improving the accuracy of gradient descent methods for complex target distributions.
method Derives finite-particle rates for regularized Stein variational gradient descent (R-SVGD).
result Establishes explicit non-asymptotic bounds for time-averaged empirical measures.

This paper solves nonparametric estimation of continuous DPPs using kernel methods.

problem Estimating continuous Determinantal Point Processes (DPPs) without assuming a parametric form.
method Developed a fixed point algorithm based on a representer theorem for nonnegative functions in RKHS.
result Demonstrated a finite-dimensional problem for nonparametric MLE of continuous DPPs.

The paper constructs finite generating sets for complex algebraic structures.

problem Finite generation of specific algebraic structures.
method Explicit construction of finite generating sets for γ2IAnγ_2 IA_n and γ2Inbγ_2\mathcal I_n^b.
result Explicit finite generating sets for γ2IAnγ_2 IA_n and almost explicit for γ2Inbγ_2\mathcal I_n^b.

New kernel models multi-output Gaussian processes accurately.

problem Challenges in modelling cross-covariances for multiple-output Gaussian processes.
method Replaced Gaussian components with block components of finite bandwidth in spectral mixture kernel.
result First multi-output generalization of spectral mixture kernel that can approximate any stationary multi-output kernel to arbitrary precision.

Empirical study shows standard CNNs deviate from NTK predictions.

problem Understanding how standard finite-width CNNs behave compared to their infinite-width NTK counterparts.
method Empirical analysis of AlexNet and LeNet architectures.
result Standard CNNs deviate significantly from their NTK counterparts, but deviation decreases with wider networks.

New groups algebraically fibre with high-dimensional hyperbolic groups.

problem Finding new quasi-isometry classes of hyperbolic groups.
method Constructing infinitely many hyperbolic groups as finite-index subgroups of right-angled Coxeter groups.
result Groups algebraically fibre with finitely presented kernels, expanding finiteness properties.

We derive and analyze a generic, recursive algorithm for estimating all splits in a finite cluster tree as well as the corresponding clusters. We further investigate statistical properties of this generic clustering algorithm when it receives level set estimates from a kernel density estimator. In particular, we derive…

2017-08-17abs ↗pdf ↗

The paper introduces a new kernel-based Maximum Mean Discrepancy (MMD) statistic for measuring the distance between two distributions given finitely-many multivariate samples. When the distributions are locally low-dimensional, the proposed test can be made more powerful to distinguish certain alternatives by incorpora…

2017-09-14abs ↗pdf ↗

The paper studies fibering properties of RACGs and random subcomplexes of buildings.

problem Higher virtual algebraic fibering properties of right-angled Coxeter groups.
method Generalization of Bestvina-Brady discrete Morse theory applied to Davis complex, combined with probabilistic arguments.
result Commutator subgroups of RACGs with certain finite building flag complexes admit epimorphisms to Z with strong topological finiteness properties.

Propose an XMSE-aware mixed estimator for EB that interpolates between ML and EB shrinkage.

problem Kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter.
method An XMSE-aware mixed estimator that interpolates between ML and EB shrinkage.
result Fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB estimator at the XMSE scale.

ULFS-KDPE estimates parameters efficiently without influence functions.

problem Estimating pathwise differentiable parameters in nonparametric models.
method Kernel debiased plug-in estimator based on universal least favorable submodel.
result Semiparametric efficiency achieved without influence function derivation.

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.

Additive principal components (APCs for short) are a nonlinear generalization of linear principal components. We focus on smallest APCs to describe additive nonlinear constraints that are approximately satisfied by the data. Thus APCs fit data with implicit equations that treat the variables symmetrically, as opposed t…

2015-11-21abs ↗pdf ↗

For all but finitely many compact orientable surfaces, we show that any superinjective map from the complex of separating curves into itself is induced by an element of the extended mapping class group. We apply this result to proving that any finite index subgroup of the Johnson kernel is co-Hopfian. Analogous propert…

2009-11-20abs ↗pdf ↗

A conservative drifting method improves generative modeling by using KDE gradients, proving convergence rates.

problem Improving generative modeling by addressing non-conservatism issues.
method Proposes a conservative drifting method using kernel density estimator gradients to address non-conservatism.
result Proves finite-particle convergence rates for the conservative method, providing explicit quadrature constants.

Improved convergence rates for Stein Variational Gradient Descent in finite-particle settings.

problem Improving convergence rates for Stein Variational Gradient Descent in finite-particle settings.
method Analyzing the time derivative of relative entropy and splitting it into dominant and smaller parts.
result Finite-particle convergence rates of order 1/\sqrt{N} for Kernelized Stein Discrepancy and Wasserstein-2 metrics.

Deep networks can be biased to learn top eigenfunctions of the kernel outside the training set.

problem Spectral bias of deep networks in the kernel regime.
method Quantitative bounds on L2L^2 difference between finite-width and infinite-width network trajectories.
result Deep networks learn top eigenfunctions of the Neural Tangent Kernel over the entire input space, not just the training set.

Generalizes neural networks for infinite-dimensional mappings, including PDE solutions.

problem Learning mappings between infinite-dimensional spaces and finite-dimensional approximations.
method Graph kernel network architecture with message passing for kernel integration.
result Competitive performance compared to state-of-the-art solvers for PDEs.

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

problem Understanding the Lipschitz continuity of feature maps associated with integral kernels.
method Analyzes differentiability assumptions to derive explicit formulas for Lipschitz constants and conditions for non-Lipschitz continuity.
result Explicit formulas and conditions for Lipschitz continuity of feature maps associated with various 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…

2013-10-21abs ↗pdf ↗