Learn-and-Adapt Stochastic Dual Gradients for Network Resource Allocation

Tianyi Chen, Qing Ling, Georgios B. Giannakis

Research output: Contribution to journalArticle

6 Scopus citations


Network resource allocation shows revived popularity in the era of data deluge and information explosion. Existing stochastic optimization approaches fall short in attaining a desirable cost-delay tradeoff. Recognizing the central role of Lagrange multipliers in a network resource allocation, a novel learn-and-adapt stochastic dual gradient (LA-SDG) method is developed in this paper to learn the sample-optimal Lagrange multiplier from historical data, and accordingly adapt the upcoming resource allocation strategy. Remarkably, an LA-SDG method only requires just an extra sample (gradient) evaluation relative to the celebrated stochastic dual gradient method. LA-SDG can be interpreted as a foresighted learning scheme with an eye on the future, or, a modified heavy-ball iteration from an optimization viewpoint. It has been established - both theoretically and empirically - that LA-SDG markedly improves the cost-delay tradeoff over state-of-the-art allocation schemes.

Original languageEnglish (US)
Article number8110688
Pages (from-to)1941-1951
Number of pages11
JournalIEEE Transactions on Control of Network Systems
Issue number4
StatePublished - Dec 2018



  • First-order method
  • network resource allocation
  • statistical learning
  • stochastic approximation

Cite this