EconBase
← All papers

Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling

Sokbae Lee, Yuan Liao, Myung Hwan Seo, Youngki Shin

arXiv 6 Jun 2021 · Statistics — Machine Learning · publishedProceedings of the AAAI Conference on Artificial Intelligence (2022) · 19 citations (OpenAlex)

arXiv:2106.03156 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We develop a new method of online inference for a vector of parameters estimated by the Polyak-Ruppert averaging procedure of stochastic gradient descent (SGD) algorithms. We leverage insights from time series regression in econometrics and construct asymptotically pivotal statistics via random scaling. Our approach is fully operational with online data and is rigorously underpinned by a functional central limit theorem. Our proposed inference method has a couple of key advantages over the existing methods. First, the test statistic is computed in an online fashion with only SGD iterates and the critical values can be obtained without any resampling methods, thereby allowing for efficient implementation suitable for massive online data. Second, there is no need to estimate the asymptotic variance and our inference method is shown to be robust to changes in the tuning parameters for SGD algorithms in simulation experiments with synthetic data.

Citation extraction

30
references
62
in-text mentions
30
distinct cited
0
self-citations
7,066
main-text words

appendix boundary found by appendix_command · 76% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Zhu, W., X. Chen, and W. B. Wu (2021) Online covariance matrix estimation in stochastic gradient descent1.000103100%
2Polyak, B. T. and A. B. Juditsky (1992) Acceleration of stochastic approximation by averaging0.874102100%
3Chen, X., J. D. Lee, X. T. Tong, and Y. Zhang (2020) Statistical inference for model parameters in stochastic gradient descent0.81142100%
4Kiefer, N. M., T. J. Vogelsang, and H. Bunzel (2000) Simple robust testing of regression hypotheses0.81142100%
5Lazarus, E., D. J. Lewis, J. H. Stock, and M. W. Watson (2018) Har inference: Recommendations for practice0.64422100%
6Zhu, Y. and J. Dong (2020) On constructing confidence region for model parameters in stochastic gradient descent via batch means0.58531100%
7Abadir, K. M. and P. Paruolo (1997) Two mixed normal densities from cointegration analysis0.51121100%
8Godichon-Baggioni, A (2017) A central limit theorem for averaged stochastic gradient algorithms in hilbert spaces and online estimation of the asymptotic va…0.51121100%
9Kushner, H. J. and J. Yang (1993) Stochastic approximation with averaging of the iterates: Optimal asymptotic rate of convergence for general processes0.51121100%
10Su, W. J. and Y. Zhu (2018) Uncertainty quantification for online learning and stochastic approximation via hierarchical incremental gradient descent0.51121100%

Showing the top 10 of 30 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Online Learning in Semiparametric Econometric Models1.00053
2SGMM: Stochastic Approximation to Generalized Method of Moments0.96194
3Fast Inference for Quantile Regression with Tens of Millions of Observations0.94163
4Robust Inference on Infinite and Growing Dimensional Time Series Regression0.40511
5csa2sls: A complete subset approach for many instruments using Stata0.40511
6SLIM: Stochastic Learning and Inference in Overidentified Models0.40511