EUVIMEDEUVIMED entdecken
Crossref

Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators

Ziyang Wei, Jiaqi Li, Likai Chen, Wei Biao Wu

IEEE Transactions on Information Theory · 2026-08 · 72 (8) · 6054-6070

DOI: 10.1109/tit.2026.3703510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2026-08. Verfasst von Ziyang Wei und 3 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and techniques, we view quantile SGD iteration as an irreducible, periodic, and positive recurrent Markov chain, which cyclically converges to its unique stationary distribution regardless of the arbitrarily fixed initialization. To derive the exact form of the stationary distribution, we analyze the structure of its characteristic function by exploiting the stationary equation. We also derive tight bounds for its moment generating function (MGF) and tail probabilities. Synthesizing the aforementioned approaches, we prove that the centered and standardized stationary distribution converges to a Gaussian distribution as the learning rate $\eta \rightarrow 0$ . This finding provides the first central limit theorem (CLT)-type theoretical guarantees for the quantile SGD estimator with constant learning rates. We further propose a recursive algorithm to construct confidence intervals of the estimators with statistical guarantees. Numerical studies demonstrate the effective finite-sample performance of the online estimator and inference procedure. The theoretical tools developed in this study are of independent interest for investigating general SGD algorithms formulated as Markov chains, particularly in non-strongly convex and non-smooth settings.

Förderung

  • NSF

Zitieren

APA

Wei, Z., Li, J., Chen, L., & Wu, W. B. (2026). Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators. IEEE Transactions on Information Theory, 72(8), 6054-6070. https://doi.org/10.1109/tit.2026.3703510

Vancouver

Wei Z, Li J, Chen L, Wu WB. Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators. IEEE Transactions on Information Theory. 2026;72(8):6054-6070. doi:10.1109/tit.2026.3703510

BibTeX
@article{Wei2026,
  author = {Wei, Ziyang and Li, Jiaqi and Chen, Likai and Wu, Wei Biao},
  title = {Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators},
  journal = {IEEE Transactions on Information Theory},
  year = {2026},
  volume = {72},
  number = {8},
  pages = {6054--6070},
  doi = {10.1109/tit.2026.3703510}
}
Kostenlos starten →