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

236471707942 · Jun 202019922001200920172026
48 results for Neural Covariance Kernel

Novel neural GP kernels learn stable, flexible covariance structures.

problem Scalable and flexible covariance kernels for Gaussian processes.
method Directly learn kriging coefficients and conditional standard deviations using deep neural architectures exploiting permutation-equivariant structure.
result Improved training stability and data efficiency with expressive, non-stationary kernels.

New kernels from ELU and GELU networks reveal non-trivial fixed points.

problem Understanding fixed-point dynamics in deep neural networks with ELU and GELU activations.
method Deriving covariance functions and analyzing fixed-point dynamics of ELU and GELU networks.
result ELU and GELU networks exhibit non-trivial fixed-point dynamics, explaining implicit regularization in overparameterized models.

Bayesian deep neural networks converge to processes with α-stable marginals under infinite variance weights.

problem Representation learning in deep kernel processes is hindered by deterministic covariance kernels.
method Showed convergence to α-stable processes with conditionally Gaussian representations in infinite-width networks.
result Conditional random covariance kernels can be recursively linked, even if the process is α-stable.

Gradient descent trains neural networks to match kernel regression's sharp generalization rate.

problem Training over-parameterized neural networks for nonparametric regression.
method Gradient descent with early stopping on over-parameterized two-layer neural networks.
result Trained neural networks achieve sharp generalization rate of O(εn2)\mathcal{O}(ε_n^2).

Extends neural network training framework to handle noise and uncertainty.

problem Handling noise and uncertainty in neural network training.
method Integrates non-zero aleatoric noise and derives posterior covariance for epistemic uncertainty.
result Derives an estimator for posterior covariance, providing a handle on epistemic uncertainty.

Kernel methods and MLPs perform similarly to linear models in high dimensions.

problem Understanding the performance of kernel methods and MLPs in high-dimensional settings.
method Analysis of kernel methods and MLPs in a high-dimensional regime with proportional asymptotics.
result Linear models are optimal in high-dimensional settings when data is generated by kernel models with nonlinear relationships.

Wide neural networks can outperform kernel methods in certain tasks.

problem Understanding when neural networks outperform kernel methods in classification tasks.
method Analyzing the performance of wide neural networks and kernel methods on various tasks, considering the initialization of SGD and the structure of covariates.
result Wide neural networks can outperform kernel methods in tasks where covariates have a low-dimensional structure similar to the target function.

Graph-based kernels improve GP performance on graph data.

problem Improving Gaussian process performance on graph-structured data.
method Introduced graph neural network-inspired kernels into Gaussian processes.
result Graph convolutional networks are equivalent to certain GP kernels when infinitely wide.

New non-separable covariance kernels for spatiotemporal data derived from harmonic oscillator physics.

problem Capturing complex spatiotemporal dependencies in Gaussian processes.
method Hybrid spectral method based on the harmonic oscillator, deriving explicit covariance kernels.
result Explicit non-separable covariance kernels with space-time interactions.

Deep Gaussian Processes are reinterpreted as deep trigonometric networks for tractable inference.

problem Challenging inference in DGPs due to intractable marginalization in latent function space.
method Viewing DGPs as deep trigonometric networks with Bochner's theorem, and using the wide limit with a bottleneck to translate DGPs into deep trigonometric networks.
result The weight space view yields the same effective covariance functions as obtained in function space, and varying prior distributions over network parameters is equivalent to employing different kernels.

This paper explores how neural network width and depth behave as they approach infinity.

problem Understanding the behavior of neural functions as width and depth go to infinity.
method Formal definition of commutativity framework, study of neural covariance kernel, novel proof techniques.
result Taking width and depth to infinity in a deep neural network with skip connections results in the same covariance structure, regardless of the order of taking limits.

The paper analyzes how Gaussian kernel parameters affect posterior covariance in Gaussian processes.

problem Understanding the influence of Gaussian kernel parameters on posterior covariance in Gaussian processes.
method Geometric analysis and a posteriori error estimation techniques from adaptive finite element methods.
result The bandwidth parameter and spatial distribution of observations significantly influence posterior covariance and its matrix.

This paper improves computational efficiency in kernel ridge regression under covariate shift.

problem Covariate shift in nonparametric regression.
method Random projections in RKHS to reduce computational demands.
result Significant computational savings can be achieved without compromising learning performance under covariate shift.

Bayesian neural networks with Mercer priors for interpretable uncertainty quantification.

problem Uncertainty quantification in neural networks, especially for complex input-to-output mappings.
method Introducing Mercer priors for BNNs, which approximate a specified GP and are scalable.
result BNNs with Mercer priors can approximate the uncertainty of a specified GP, making them interpretable and scalable.

Deep neural networks for structured prediction using kernel-induced losses.

problem Structured prediction tasks for images and texts.
method Designing a novel family of deep neural architectures that predict in a finite-dimensional subspace derived from the kernel-induced loss.
result Gradient descent algorithms can be used for structured prediction with deep neural networks.

The paper analyzes how re-weighting helps in reducing variance in high-dimensional kernel methods under covariate shifts.

problem The challenge of high-dimensional kernel methods under covariate shifts and the role of re-weighting.
method Derives asymptotic expansion of high-dimensional kernels under covariate shifts, analyzes bias-variance decomposition, and characterizes the regularized kernel.
result Re-weighting helps in decreasing variance and can be seen as a data-dependent regularization.

A new model DKMPP integrates covariates and uses an integration-free method for spatio-temporal point processes.

problem Training intractable deep spatio-temporal point processes with multimodal covariates.
method DKMPP uses a deep kernel to model complex relationships and an integration-free score matching method.
result DKMPP and score-based estimators outperform baseline models in spatio-temporal point processes.

Paper connects neural networks to Gaussian processes for understanding double-descent.

problem Understanding the double-descent phenomenon in neural networks.
method Uses techniques from random matrix theory and Gaussian processes.
result Establishes a connection between NNGP and random matrix theory for neural networks.

Kernel εε-Greedy optimizes multi-armed bandits with covariates for sub-linear regret.

problem Optimizing multi-armed bandits with covariates in a reproducing kernel Hilbert space.
method Online weighted kernel ridge regression estimator for mean reward function estimation.
result Achieves sub-linear regret rate and optimal T\sqrt{T} regret rate under margin condition.

We study the problem of structured output learning from a regression perspective. We first provide a general formulation of the kernel dependency estimation (KDE) problem using operator-valued kernels. We show that some of the existing formulations of this problem are special cases of our framework. We then propose a c…

2012-05-10abs ↗pdf ↗

This monograph develops the theory of covariant Schrödinger semigroups acting on sections of vector bundles over noncompact Riemannian manifolds from scratch. Contents: I. Sobolev spaces on vector bundles II. Smooth heat kernels on vector bundles III. Basis differential operators in Riemannian manifolds IV. Some specif…

2018-01-04abs ↗pdf ↗

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.

Deep kernel learning combines the non-parametric flexibility of kernel methods with the inductive biases of deep learning architectures. We propose a novel deep kernel learning model and stochastic variational inference procedure which generalizes deep kernel learning approaches to enable classification, multi-task lea…

2016-11-01abs ↗pdf ↗

This paper shows how infinitely wide Tensor Networks converge to Gaussian Processes.

problem Understanding the relationship between Tensor Networks and Gaussian Processes.
method Analyzing the infinite-width limit of Tensor Networks and comparing them to Gaussian Processes.
result Infinitely wide Tensor Networks converge to Gaussian Processes, proving their equivalence.

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.

Convolution and pooling improve kernel methods in image classification.

problem Understanding the interplay between approximation and generalization in convolutional architectures.
method Characterized RKHS of kernels with convolution, pooling, and downsampling, computed generalization error.
result Convolution and pooling operations trade off approximation with generalization power.

Study eigenvalues and eigenvectors in neural networks, focusing on signal propagation.

problem Characterize signal eigenvalues and eigenvectors in neural networks.
method Characterizes signal eigenvalues and eigenvectors for a nonlinear spiked covariance model.
result Provides precise quantitative characterizations of signal eigenvalues and eigenvectors in neural networks.

Deconfounds neural network representation similarity metrics to improve consistency and accuracy.

problem Confounding by population structure in similarity metrics like RSA and CKA.
method Covariate adjustment regression to adjust for confounders.
result Improves detection of semantically similar neural networks and consistency in transfer learning.

It has long been known that a single-layer fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP), in the limit of infinite network width. This correspondence enables exact Bayesian inference for infinite width neural networks on regression tasks by means of eva…

2017-11-01abs ↗pdf ↗

This work extends Gaussian process priors to neural operators for function space mappings.

problem Improving uncertainty quantification in deep neural networks.
method Extending Gaussian process priors to neural operators with conditions for convergence and computation of covariance functions.
result Arbitrary-depth neural operators with Gaussian kernels converge to function-valued GPs, enabling posterior computation in regression scenarios.

We propose a method for feature selection that employs kernel-based measures of independence to find a subset of covariates that is maximally predictive of the response. Building on past work in kernel dimension reduction, we show how to perform feature selection via a constrained optimization problem involving the tra…

2017-07-04abs ↗pdf ↗

The expressive power of Gaussian processes depends heavily on the choice of kernel. In this work we propose the novel harmonizable mixture kernel (HMK), a family of expressive, interpretable, non-stationary kernels derived from mixture models on the generalized spectral representation. As a theoretically sound treatmen…

2018-10-10abs ↗pdf ↗

Develops efficient inference for noise heterogeneity in machine learning models.

problem Downstream procedures based on residuals can be biased in additive noise models.
method Semiparametrically efficient inference using a novel Hilbert-valued one-step estimator.
result Constructs tests and confidence intervals for residual independence and goodness of fit.

Neighborhood sampling affects graph neural network training outcomes.

problem Understanding the impact of neighborhood sampling on graph neural network training.
method Theoretical analysis using neural tangent kernels and Gaussian processes.
result Posterior covariance differs for different neighborhood sampling approaches, indicating no dominant approach.

Optimally tackles covariate shift in RKHS-based nonparametric regression.

problem Covariate shift in nonparametric regression over RKHS.
method Two families of covariate shift problems defined using likelihood ratios. Minimax rate-optimal estimators for KRR and reweighted KRR.
result KRR is minimax rate-optimal and strictly sub-optimal compared to naive estimator under covariate shift.

Gaussian Processes (GPs) provide a general and analytically tractable way of modeling complex time-varying, nonparametric functions. The Automatic Bayesian Covariance Discovery (ABCD) system constructs natural-language description of time-series data by treating unknown time-series data nonparametrically using GP with …

2015-11-26abs ↗pdf ↗