Learn-and-adapt network resource allocation

Recognizing the central role of Lagrange multipliers in network resource allocation, a novel learn-and-adapt stochastic dual gradient (LA-SDG) method is developed in this paper to learn the empirical optimal Lagrange multiplier from historical data, and adapt to the upcoming resource allocation strategy. Remarkably, it only requires one more sample (gradient) evaluation than the celebrated stochastic dual gradient (SDG) method. LA-SDG can be interpreted as a foresighted learning approach with an eye on the future. It is established — both theoretically and empirically — that LA-SDG markedly improves the cost-delay tradeoff over state-of-the-art network resource allocation schemes.