Stochastic Gradient Descent with Adaptive Data
Operations Research · 2026-07 · 74 (4) · 2113-2145
DOI: 10.1287/opre.2024.1014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Operations Research, 2026-07. Verfasst von Ethan Che und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben.
Abstract (Originalsprache)
Stochastic Gradient Descent with Adaptive Data Stochastic gradient descent (SGD) is a central tool in modern optimization, but its classical theory relies on the assumption that data are independent of the decisions being optimized. In many operations research settings, this assumption fails: policies influence system dynamics, and the resulting data feed back into subsequent updates. In “Stochastic Gradient Descent with Adaptive Data,” Che, Dong, and Tong address this challenge by developing a general framework for analyzing SGD when data are generated adaptively by policy-dependent Markov processes. Their analysis shows that fully adaptive SGD can still attain convergence rates comparable to the classical i.i.d. setting, provided the underlying system satisfies mild ergodicity and continuity conditions. The theory is illustrated through canonical applications in operations research and reinforcement learning. Overall, the paper provides rigorous and reassuring theoretical foundations for deploying learning algorithms in dynamic environments where decisions and data are fundamentally intertwined.
Zitieren
APA
Che, E., Dong, J., & Tong, X. T. (2026). Stochastic Gradient Descent with Adaptive Data. Operations Research, 74(4), 2113-2145. https://doi.org/10.1287/opre.2024.1014
Vancouver
Che E, Dong J, Tong XT. Stochastic Gradient Descent with Adaptive Data. Operations Research. 2026;74(4):2113-2145. doi:10.1287/opre.2024.1014
BibTeX
@article{Che2026,
author = {Che, Ethan and Dong, Jing and Tong, Xin T.},
title = {Stochastic Gradient Descent with Adaptive Data},
journal = {Operations Research},
year = {2026},
volume = {74},
number = {4},
pages = {2113--2145},
doi = {10.1287/opre.2024.1014}
}
EUVIMED