Existing resource allocation approaches for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements. The present paper leverages online learning advances to facilitate online resource allocation tasks. By recognizing the central role of Lagrange multipliers, the underlying constrained optimization problem is formulated as a machine learning task involving both training and operational modes, with the goal of learning the sought multipliers in a fast and efficient manner. To this end, an order-optimal offline learning approach is developed first for batch training, and it is then generalized to the online setting with a procedure termed learn-and-adapt. The novel resource allocation protocol permeates benefits of stochastic approximation and statistical learning to obtain low-complexity online updates with learning errors close to the statistical accuracy limits, while still preserving adaptation performance, which in the stochastic network optimization context guarantees queue stability. Analysis and simulated tests demonstrate that the proposed data-driven approach improves the delay and convergence performance of existing resource allocation schemes.
Bibliographical noteFunding Information:
This work was supported in part by NSF 1509040, 1508993, 1423316, 1514056, 1500713, 1509005, 0952867, and in part by ONR N00014-12-1-0997; and in part by the National Natural Science Foundation of China under Grant 61671154. This paper was presented in part at the IEEE Global Conference on Signal Information Processing,Washington, DC, USA, December 7-9, 2016.
© 1991-2012 IEEE.
- Stochastic optimization
- network resource allocation
- statistical learning
- stochastic approximation