Statistical inference for model parameters in stochastic gradient descent
From MaRDI portal
Publication:2176618
DOI10.1214/18-AOS1801zbMath1440.62287arXiv1610.08637OpenAlexW3007705674MaRDI QIDQ2176618
Xi Chen, Jason D. Lee, Yi-Chen Zhang, Xin Thomson Tong
Publication date: 5 May 2020
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1610.08637
asymptotic variancestochastic gradient descenthigh-dimensional inferencetime-inhomogeneous Markov chainbatch-means estimator
Interacting random processes; statistical mechanics type models; percolation theory (60K35) Analysis of variance and covariance (ANOVA) (62J10) Markov processes: hypothesis testing (62M02)
Related Items
Online statistical inference for parameters estimation with linear-equality constraints, Convergence acceleration of ensemble Kalman inversion in nonlinear settings, Parameter calibration in wake effect simulation model with stochastic gradient descent and stratified sampling, Statistical inference for model parameters in stochastic gradient descent, A probability approximation framework: Markov process approach, Online Covariance Matrix Estimation in Stochastic Gradient Descent, First-Order Newton-Type Estimator for Distributed Estimation and Inference, Unnamed Item, Bridging the gap between constant step size stochastic gradient descent and Markov chains, Two-stage communication-efficient distributed sparse M-estimation with missing data, An Asymptotic Analysis of Random Partition Based Minibatch Momentum Methods for Linear Regression Models, Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning, Estimation and inference by stochastic optimization, Unnamed Item, Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach, Unnamed Item, Neural ODEs as the deep limit of ResNets with constant weights, Statistical Inference for Online Decision Making via Stochastic Gradient Descent, Unnamed Item, One-dimensional system arising in stochastic gradient descent
Cites Work
- Unnamed Item
- Unnamed Item
- On asymptotically optimal confidence regions and tests for high-dimensional models
- A general theory of hypothesis tests and confidence regions for sparse high dimensional models
- Statistics for high-dimensional data. Methods, theory and applications.
- Fast global convergence of gradient methods for high-dimensional statistical recovery
- Estimating the asymptotic variance with batch means
- Least squares after model selection in high-dimensional sparse models
- Statistical inference for model parameters in stochastic gradient descent
- High-dimensional variable screening and bias in subsequent inference, with an empirical comparison
- Batch means and spectral variance estimators in Markov chain Monte Carlo
- Asymptotic and finite-sample properties of estimators based on stochastic gradients
- Confidence level solutions for stochastic programming
- High-dimensional graphs and variable selection with the Lasso
- Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
- Introduction to Uncertainty Quantification
- p-Values for High-Dimensional Regression
- Fixed-Width Output Analysis for Markov Chain Monte Carlo
- Simulation Output Analysis Using Standardized Time Series
- Robust Stochastic Approximation Approach to Stochastic Programming
- Strong Consistency and Other Properties of the Spectral Variance Estimator
- Acceleration of Stochastic Approximation by Averaging
- Sure Independence Screening for Ultrahigh Dimensional Feature Space
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
- A Proximal Stochastic Gradient Method with Progressive Variance Reduction
- On Asymptotic Normality in Stochastic Approximation
- Confidence Intervals for Low Dimensional Parameters in High Dimensional Linear Models
- A Stochastic Approximation Method
