Online Covariance Matrix Estimation in Stochastic Gradient Descent

DOI10.1080/01621459.2021.1933498arXiv2002.03979OpenAlexW3165394516MaRDI QIDQ6107216

No author found.

Publication date: 3 July 2023

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.03979

zbMATH Keywords

asymptotic normalitystatistical inferencerecursiveaveraging stochastic gradient descent

Mathematics Subject Classification ID

Statistics (62-XX) Online algorithms; streaming algorithms (68W27)

Related Items (2)

An Asymptotic Analysis of Random Partition Based Minibatch Momentum Methods for Linear Regression Models ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Empirical likelihood methods with weakly dependent processes
• On power series diverging everywhere on the circle of convergence
• Recursive estimation of time-average variance constants
• Estimating the asymptotic variance with batch means
• Subsampling
• Resampling methods for dependent data
• Theoretical comparisons of block bootstrap methods
• Statistical inference for model parameters in stochastic gradient descent
• Batch means and spectral variance estimators in Markov chain Monte Carlo
• Asymptotic and finite-sample properties of estimators based on stochastic gradients
• A nonstandard empirical likelihood for time series
• Computer-intensive rate estimation, diverging statistics and scanning
• An optimal algorithm for stochastic strongly-convex optimization
• Scalable statistical inference for averaged implicit stochastic gradient descent
• Fixed-Width Output Analysis for Markov Chain Monte Carlo
• Acceleration of Stochastic Approximation by Averaging
• Analysis of recursive stochastic algorithms
• Multivariate output analysis for Markov chain Monte Carlo
• Statistical Inference for the Population Landscape via Moment-Adjusted Stochastic Gradients
• A Progressive Block Empirical Likelihood Method for Time Series
• On Asymptotic Normality in Stochastic Approximation
• Asymptotic Distribution of Stochastic Approximation Procedures
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one
• Stochastic approximation

This page was built for publication: Online Covariance Matrix Estimation in Stochastic Gradient Descent