English

On Constructing Confidence Region for Model Parameters in Stochastic Gradient Descent via Batch Means

Machine Learning 2020-02-03 v2 Machine Learning Statistics Theory Statistics Theory

Abstract

In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method. The main idea is to cancel out the covariance matrix which is hard/costly to estimate. In the process of developing the algorithm, we establish process-level functional central limit theorem for Polyak-Ruppert averaging based stochastic gradient descent estimators. We also extend the batch means method to accommodate more general batch size specifications.

Keywords

Cite

@article{arxiv.1911.01483,
  title  = {On Constructing Confidence Region for Model Parameters in Stochastic Gradient Descent via Batch Means},
  author = {Yi Zhu and Jing Dong},
  journal= {arXiv preprint arXiv:1911.01483},
  year   = {2020}
}
R2 v1 2026-06-23T12:04:37.841Z