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

3673109145 · May 202619922001200920172026
48 results for spectral decay

The spectral kk-support norm enjoys good estimation properties in low rank matrix learning problems, empirically outperforming the trace norm. Its unit ball is the convex hull of rank kk matrices with unit Frobenius norm. In this paper we generalize the norm to the spectral (k,p)(k,p)-support norm, whose additional para…

2016-01-04abs ↗pdf ↗

New bounds for KRR condition number reveal overfitting phenomena.

problem Characterizing overfitting in KRR with varying kernel spectral decay.
method Derived new bounds for kernel matrices, enhanced test error bounds, and identified feature independence role.
result Identified tempered and catastrophic overfitting phenomena.

Study examines wave equation decay and Strichartz estimates on conic manifolds.

problem Analyzing wave equation behavior on conic spaces with critical electromagnetic potentials.
method Established decay and Strichartz estimates through localized spectral measure construction.
result Extended and improved previous results on wave equation behavior with critical potentials.

Improved performance of factorized neural layers through spectral initialization and Frobenius decay.

problem Improving the performance of factorized neural layers in various deep learning contexts.
method Spectral initialization and Frobenius decay for initialization and regularization.
result Spectral initialization and Frobenius decay lead to improved performance across multiple deep learning settings.

Spectral feature learning improves IV regression for causal effect estimation.

problem Estimating causal effects in the presence of hidden confounders.
method Two-stage least squares estimator based on spectral features.
result Performance of the method depends on strong spectral alignment and slow eigenvalue decay.

Study shows rapid decay of Hitchin metric from semi-flat metric on Higgs bundles.

problem Analyzing the asymptotic behavior of the Hitchin metric on moduli spaces of Higgs bundles.
method Examined the decay rate of the difference between Hitchin and semi-flat metrics on smooth spectral curves.
result Exponential decay of the difference between Hitchin and semi-flat metrics as t approaches infinity.

Global stability proved for Navier-Stokes equations on hyperbolic space.

problem Stability of the Navier-Stokes equations on hyperbolic space.
method Proved global stability with exponential decay rate for small initial data.
result Exponential decay rate of $μλ_\Def^{(3)}$ for Navier-Stokes equations on hyperbolic space.

Unified analysis of kernel-based and locally adaptive bandit optimization methods.

problem Performance of bandit optimization algorithms in RKHS functions.
method Investigates the relationship between kernel regularity and algorithmic performance, characterizing spectral properties of various kernels.
result Unified framework for analyzing kernel-based and locally adaptive bandit algorithms, deriving explicit regret bounds.

The study improves norms of spectral projectors on specific surfaces.

problem Improving the L2oLL^2 o L^{\infty} norm of spectral projectors on certain surfaces.
method Quantum Integrability, joint basis of eigenfunctions, Lagrangian oscillatory functions, caustics, BKW decay.
result Polynomial improvement on the L2oLL^2 o L^{\infty} norm for generic simple spheres of revolution and the Euclidean disk.

S2D selectively decays large singular values to improve quantization of neural activations.

problem Large activation outliers in transformer models cause accuracy drops during quantization.
method Selective Spectral Decay (S2DS^2D) that surgically regularizes only the largest singular values.
result Significantly reduces activation outliers and produces well-conditioned representations.

Study on variance of Laplace eigenfunctions on manifolds.

problem Investigating the variance of Laplace eigenfunctions on compact manifolds.
method Combining Kac-Rice formula, Wiener-Itô chaos decompositions, and pointwise Weyl law analysis.
result Established a quantitative bound for the fluctuations of nodal volumes, improving existing results.

New Hermite approximations accelerate convergence with adaptive coordinate transformations.

problem Accelerating convergence of spectral approximations for Hermite expansions.
method Using normalizing flows for adaptive coordinate transformations and deriving error estimates.
result Error estimates for Hermite expansions under adaptive coordinate transformations.

Study tackles distribution shift in combinatorial settings using matrix completion techniques.

problem Tackling distribution shift in combinatorial settings with rigorous statistical guarantees.
method Develops novel algorithms and theoretical results for extrapolating to test distributions not covered in training.
result Achieves bilinear combinatorial extrapolation under gradual spectral decay in high-dimensional data.

We study the spectral gap of the Erdős--Rényi random graph through the connectivity threshold. In particular, we show that for any fixed δ>0δ> 0 if p(1/2+δ)lognn,p \ge \frac{(1/2 + δ) \log n}{n}, then the normalized graph Laplacian of an Erdős--Rényi graph has all of its nonzero eigenvalues tightly concentrated around 11. We est…

2012-01-02abs ↗pdf ↗

LASE improves local network structure visualization by targeting locally low-dimensional regions.

problem Global spectral embedding fails to capture local geometric features in sparse, transitive networks.
method Local Adjacency Spectral Embedding (LASE) using weighted spectral decomposition.
result LASE reveals locally low-dimensional structure, improving local reconstruction and visualization.

New methods improve tree ensemble models by compressing them while maintaining accuracy.

problem Theoretical understanding and practical compression of tree ensembles like random forests and gradient boosting machines.
method Spectral perspective on tree ensembles, deriving minimax rates and developing compression schemes.
result Leading eigenfunctions/singular vectors capture dominant predictive directions, leading to smaller, competitive models.

We study the distribution of resonances for geometrically finite hyperbolic surfaces of infinite area by countting resonances numerically. The resonances are computed as zeros of the Selberg zeta function, using an algorithm for computation of the zeta function for Schottky groups. Our particular focus is on three aspe…

2013-05-21abs ↗pdf ↗

Fiedler regularization uses spectral graph theory to improve neural network performance.

problem Improving neural network performance by penalizing weights based on connectivity.
method Uses the Fiedler value of the neural network's graph as a regularization tool, providing theoretical and computational methods.
result Demonstrates Fiedler regularization's effectiveness in improving neural network performance.

Unified framework explains why overfitting is benign in interpolating learning.

problem Understanding why overfitting is benign in highly overparameterized models.
method Spectral-transport stability framework.
result Sharp benign-overfitting criterion and explicit phase-transition rates.

Method detects neural network equivalence via matrix ensembles and spectral analysis.

problem Detecting equivalence among different deep learning architectures.
method Generating Mixed Matrix Ensembles (MMEs) and matching to conjugate circular ensembles.
result Empirical evidence shows vanishing differences in spectral densities with long tail decay rates.

We introduce a novel algorithm that computes the kk-sparse principal component of a positive semidefinite matrix AA. Our algorithm is combinatorial and operates by examining a discrete set of special vectors lying in a low-dimensional eigen-subspace of AA. We obtain provable approximation guarantees that depend on t…

2013-03-03abs ↗pdf ↗

Power-law spectrum of random feature model is preserved in neural networks.

problem Preserving power-law spectrum in neural networks through random feature model.
method Characterized eigenvalues of population random-feature covariance using dyadic head-tail decomposition and Wick chaos expansions.
result Power-law exponent αα is inherited from input covariance, modified by a logarithmic correction.

Generative Adversarial Networks (GANs), though powerful, is hard to train. Several recent works (brock2016neural,miyato2018spectral) suggest that controlling the spectra of weight matrices in the discriminator can significantly improve the training of GANs. Motivated by their discovery, we propose a new framework for t…

2018-12-28abs ↗pdf ↗

Study uncovers scaling laws and spectral properties of shallow neural networks.

problem Understanding scaling laws and spectral properties of shallow neural networks.
method Leveraging connections with matrix compressed sensing and LASSO, derived a phase diagram for excess risk.
result Uncovered crossovers between scaling regimes and plateau behaviors, validated empirical observations.

The salient properties of large empirical covariance and correlation matrices are studied for three datasets of size 54, 55 and 330. The covariance is defined as a simple cross product of the returns, with weights that decay logarithmically slowly. The key general properties of the covariance matrices are the following…

2009-03-09abs ↗pdf ↗

The energy in a square membrane ΩΩ subject to constant viscous damping on a subset ωΩω\subset Ω decays exponentially in time as soon as ωω satisfies a geometrical condition known as the "Bardos-Lebeau-Rauch" condition. The rate τ(ω)τ(ω) of this decay satisfies τ(ω)=2min(μ(ω),g(ω))τ(ω)= 2 \min(-μ(ω), g(ω)) (see Lebeau [Math. Phys. Stud. …

2007-06-01abs ↗pdf ↗

GenMod uses generative models to approximate high-dimensional PDE solutions with limited evaluations.

problem Quantifying uncertainty in high-dimensional PDE systems with random parameters.
method Develops a method using generative models to approximate polynomial chaos coefficients in underdetermined systems.
result The method outperforms sparsity-promoting methods in approximating PDE solutions with limited evaluations.

Bayesian framework for sphere regression using Gaussian fields.

problem Nonparametric regression on the sphere with Gaussian priors.
method Isotropic Gaussian field priors, harmonic structure, exact posterior distributions, optimal spectral truncation, posterior contraction rates.
result Sharp posterior contraction rates for Gaussian priors with polynomially decaying angular power spectra.

New gauge preserves Einstein metrics' interactions, proving rigidity on negatively curved manifolds.

problem Stability and deformation theory of Einstein metrics.
method Introduces Chen-Nagano gauge condition, linking Lichnerowicz Laplacian to shifted scalar operator.
result Chen-Nagano gauge collapses to classical transverse-traceless gauge under spectral pinching assumptions.

Persistence diagrams from random matrices follow RMT universality, offering a new spectral diagnostic.

problem Understanding spectral properties of random matrices using topological data analysis.
method Applying Morse theory to persistence diagrams of quadratic forms restricted to unit spheres.
result Persistence entropy outperforms traditional level spacing ratios in discriminating random matrix ensembles.

Improved model for non-smooth signals with complex spectra.

problem Current models struggle with non-smooth signals and complex spectral structures.
method CGPCM and RGPCM models with causality and Bayesian nonparametric interpretations, improved variational inference.
result Proposed models show better performance on synthetic and real-world data.