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

107213320426 · Jun 202019922001200920172026
48 results for gradient covariance

New method improves online covariance estimation for SGD.

problem Improving online covariance estimation for SGD.
method Proposes a de-biased covariance estimator that eliminates second-order derivatives.
result Achieves a convergence rate of n(α1)/2lognn^{(α-1)/2} \sqrt{\log n}, outperforming existing methods.

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and the covariance structure of gradient noise are critical for regularization, it remains unclear whether or not the class of noise distribution…

2019-06-18abs ↗pdf ↗

The paper optimizes regret using covariance between costs and decisions.

problem Optimizing expected regret in decision-making problems.
method Developed derivative theory of covariance regret functional, derived Gâteaux derivative, and extended to constrained optimization.
result Gradient of covariance regret is the cost covariance matrix, with implications for portfolio optimization.

GBMixed boosts mixed models for clustered data, estimating mean and variance flexibly.

problem Flexible estimation of mean and variance components in clustered data.
method Gradient Boosting framework for linear mixed models with likelihood-based gradients.
result GBMixed accurately recovers complex nonlinear fixed effects and covariances.

Vanilla SGD learns SIM from anisotropic data without explicit covariance estimation.

problem Learning SIM from anisotropic Gaussian inputs.
method Vanilla Stochastic Gradient Descent (SGD) trained on SIM with anisotropic input.
result Vanilla SGD adapts to anisotropic data's covariance structure.

This short note reviews so-called Natural Gradient Descent (NGD) for multivariate Gaussians. The Fisher Information Matrix (FIM) is derived for several different parameterizations of Gaussians. Careful attention is paid to the symmetric nature of the covariance matrix when calculating derivatives. We show that there ar…

2020-01-27abs ↗pdf ↗

Paper examines the structure of stochastic gradients in deep learning.

problem Exploring the structure and heavy tails of stochastic gradients in deep learning.
method Conducted formal statistical tests on stochastic gradients and gradient noise.
result Stochastic gradients and gradient noise do not exhibit power-law heavy tails, but their covariance spectra do.

Square-root natural-gradient improves variational inference convergence.

problem Challenges in establishing theoretical convergence guarantees for natural-gradient descent.
method Square-root parameterization for Gaussian covariance.
result Establishes novel convergence guarantees for natural-gradient Gaussian inference.

Optimizes SGLD noise structure for better generalization bounds.

problem Improving generalization bounds for large models trained with SGLD.
method Manipulates the noise structure in SGLD to optimize information-theoretical bounds.
result Optimal noise covariance is the square root of the expected gradient covariance under certain constraints.

This paper analyzes generalization for linear models with spiked covariance structures.

problem Understanding the generalization performance of linear models with spiked covariance structures.
method Derives the generalization error for two simple models with spiked covariances using random matrix theory.
result The eigenvector and eigenvalue corresponding to the spike significantly influence the generalization error.

When training a machine learning model with observational data, it is often encountered that some values are systemically missing. Learning from the incomplete data in which the missingness depends on some covariates may lead to biased estimation of parameters and even harm the fairness of decision outcome. This paper …

2018-12-21abs ↗pdf ↗

Study mini-batch SGD noise and its limits, proving complexity guarantees.

problem Analyzing the noise in mini-batch SGD and its impact on optimization.
method Examined the conditional covariance and diffusion limits of SGD under different sampling designs.
result Proved mean-square upper bounds and Fisher van Trees lower bounds for SGD, linking them to effective dimension and condition number.

A scalable algorithm for GP regression selects relevant covariates efficiently.

problem Scalable variable selection in large GP regression models.
method VGPR algorithm using Vecchia approximation for sparse precision matrix, mini-batch subsampling.
result Improved scalability and accuracy in selecting relevant covariates.

Study shows how mini-batch GD with random reshuffling affects least squares regression dynamics.

problem Analyzing the error dynamics of mini-batch GD with random reshuffling for least squares regression.
method Represented training and generalization errors through a sample cross-covariance matrix Z, compared with sample covariance matrix of original features X, and used linear scaling rule for analysis.
result Mini-batch GD with random reshuffling exhibits subtle step-size dependence not detectable by gradient flow analysis, converging to a limit dependent on the step size.

The study analyzes the evolution of Gaussian measures under a specific gradient flow.

problem Analyzing the evolution of Gaussian measures under a specific gradient flow.
method Derives ordinary differential equations governing the evolution of mean, covariance, and mass under the HK-Boltzmann gradient flow.
result Exponential convergence to equilibrium demonstrated through Polyak-Lojasiewicz-type inequalities.

This work investigates how gradient-based learning performs with structured data, revealing issues and improvements.

problem Gradient-based learning under structured data, particularly with a spiked covariance structure.
method Investigates the effect of a spiked covariance structure on gradient-based feature learning and proposes weight normalization.
result Gradient-based dynamics may fail to recover the true direction in anisotropic settings, but weight normalization can improve performance.

Paper presents a rank-1 approximation method for natural policy gradients in deep RL.

problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.

New findings on optimization landscape of Toeplitz covariance estimation.

problem Understanding the geometry of the Gaussian maximum-likelihood objective for Toeplitz covariance estimation.
method Overparameterized Carathéodory representation of positive definite Toeplitz covariance matrices, focusing on both amplitudes and frequencies.
result Joint optimization of amplitudes and frequencies leads to a benign population landscape, allowing for global recovery of the true Toeplitz covariance.

A new model for dynamic covariance recovery in neuroimaging data.

problem Estimating time-varying covariances in high-dimensional neuroimaging data.
method Nonconvex factorization into sparse spatial and smooth temporal components, combined with spectral initialization and gradient descent.
result The proposed method achieves linear convergence and superior performance compared to existing approaches.

We present Natural Gradient Boosting (NGBoost), an algorithm for generic probabilistic prediction via gradient boosting. Typical regression models return a point estimate, conditional on covariates, but probabilistic regression models output a full probability distribution over the outcome space, conditional on the cov…

2019-10-08abs ↗pdf ↗

Gradient descent outperforms ridge regression under certain covariance matrix decay conditions.

problem Comparing the performance of gradient descent and ridge regression in linear models.
method Investigated gradient descent and ridge regression for linear regression with random isotropic ground truth.
result Gradient descent outperforms ridge regression under specific covariance matrix decay conditions.

SpecGD mitigates misalignment in phase retrieval models with anisotropic inputs.

problem Misalignment during gradient descent in phase retrieval models with anisotropic inputs.
method Spectral gradient descent modifies gradient updates to preserve directional information and remove spike amplification.
result SpecGD removes spike amplification, leading to stable alignment and accelerated noise contraction.

Enhances GBDT robustness with one-hot encoding and regularization.

problem Low robustness of GBDT models against covariate perturbation.
method One-hot encoding to linear framework, risk decomposition, L1L_1 or L2L_2 regularization.
result Regularization enhances GBDT robustness.

Improved stability for large-scale Bayesian sampling.

problem Reducing instability in Langevin dynamics for large datasets.
method Introducing a modified CCAdL thermostat with a scaling and squaring method and a truncated Taylor series approximation.
result Significantly improved numerical stability and accuracy over existing methods.

Random matrix theory explains transient signal detectability in early-stopped gradient flow.

problem Transient signal detectability in early-stopped gradient flow.
method Random matrix theory applied to gradient flow in a linear teacher-student setting.
result Transient Baik-Ben Arous-Péché (BBP) transition in learning dynamics due to anisotropy and noise.

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).

New method for zeroth-order stochastic gradient algorithms provides confidence intervals.

problem Lack of inferential capabilities for zeroth-order stochastic gradient algorithms.
method Established central limit theorem and provided online estimators for asymptotic covariance matrix.
result Asymptotically valid confidence sets for parameter estimation and prediction.

Study improves covariance estimation for SGD under Markovian data, matching best rates.

problem Improving covariance estimation for SGD in Markovian data settings.
method Online overlapping batch-means covariance estimator for SGD under Markovian sampling.
result Established convergence rates for covariance estimation under Markovian sampling.

Spectral measurements reveal hidden representation geometry in language model training.

problem Hidden internal representation in language model training is hard to examine.
method Empirical protocol using activation covariance and per-sample gradient SVD spectra.
result Batch size affects representation geometry, and activation spectra predict token efficiency.

The stochastic gradient descent (SGD) algorithm is widely used for parameter estimation, especially for huge data sets and online learning. While this recursive algorithm is popular for computation and memory efficiency, quantifying variability and randomness of the solutions has been rarely studied. This paper aims at…

2020-02-10abs ↗pdf ↗