Journal article · 2026 · Open access

Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control

Xiang Li, Jiadong Liang, Xinyun Chen, Zhihua Zhang

Operations Research, 74(4), 2034–2052 · Published 28 January 2026 · DOI 10.1287/opre.2025.1662

Open PDFView at the publisherCite this paper

In brief

“Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control” is a 2026 journal article by Xiang Li and 3 co-authors, published in Operations Research. OpenAlex counts 11 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
11
Most cited in
2026 (9)
Field-weighted impact
9.73
References
60
Authors
4

Abstract

Stream SGD: Fast Learning and Valid Inference from Dependent Data Many online optimization problems in operations research rely on data generated by Markovian systems whose dynamics depend on the decision parameters, creating both statistical dependence and biased gradient information. This paper, “Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control,” develops a unified theory for stream stochastic gradient descent (SGD), a sample-efficient method that uses just one observation per iteration. Using Poisson-equation techniques, the authors quantify and control gradient bias and dependence, proving an optimal [Formula: see text] convergence rate and a state-of-the-art O(log T) regret bound. Beyond optimization performance, the paper introduces an online inference framework for uncertainty quantification and establishes a functional central limit theorem that underpins valid asymptotic inference. A new Wasserstein-type divergence yields verifiable conditions via coupling arguments tailored to operations research models. Applications to queueing and inventory problems demonstrate how the theory translates into practical, scalable algorithms.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, X., Liang, J., Chen, X., & Zhang, Z. (2026). Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control. Operations Research, 74(4), 2034–2052. https://doi.org/10.1287/opre.2025.1662

MLA 9

Li, Xiang, et al. “Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control.” Operations Research, vol. 74, no. 4, 2026, pp. 2034–2052. https://doi.org/10.1287/opre.2025.1662.

Chicago

Li, Xiang, Jiadong Liang, Xinyun Chen, and Zhihua Zhang. 2026. “Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control.” Operations Research 74 (4): 2034–2052. https://doi.org/10.1287/opre.2025.1662.

Harvard

Li, X. et al. (2026) ‘Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control’, Operations Research, 74(4), pp. 2034–2052. doi:10.1287/opre.2025.1662.

IEEE

X. Li, J. Liang, X. Chen, and Z. Zhang, “Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control,” Operations Research, vol. 74, no. 4, pp. 2034–2052, 2026, doi: 10.1287/opre.2025.1662.

BibTeX

@article{li2026convergence,
  title     = {{Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control}},
  author    = {Li, Xiang and Liang, Jiadong and Chen, Xinyun and Zhang, Zhihua},
  journal   = {Operations Research},
  year      = {2026},
  volume    = {74},
  number    = {4},
  pages     = {2034--2052},
  doi       = {10.1287/opre.2025.1662},
  url       = {https://doi.org/10.1287/opre.2025.1662}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202411
202511
202699

Its field-weighted citation impact is 9.73: it has been cited 9.73 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques

  • online optimization
  • Markovian systems
  • gradient bias
  • statistical dependence
  • Poisson equation
  • convergence rate
  • regret bounds
  • online inference

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, X., Liang, J., Chen, X., & Zhang, Z. (2026). Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control. Operations Research, 74(4), 2034–2052. https://doi.org/10.1287/opre.2025.1662

How many times has this paper been cited?

11 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Xiang Li, Jiadong Liang, Xinyun Chen, Zhihua Zhang.

What is the DOI of this paper?

10.1287/opre.2025.1662, permanently at https://doi.org/10.1287/opre.2025.1662. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.