Abstract
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.
| Original language | English (US) |
|---|---|
| Title of host publication | 18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1-5 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781509030088 |
| DOIs | |
| State | Published - Dec 19 2017 |
| Event | 18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017 - Sapporo, Japan Duration: Jul 3 2017 → Jul 6 2017 |
Publication series
| Name | IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC |
|---|---|
| Volume | 2017-July |
Other
| Other | 18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017 |
|---|---|
| Country/Territory | Japan |
| City | Sapporo |
| Period | 7/3/17 → 7/6/17 |
Bibliographical note
Funding Information:Work in this paper was supported by NSF 1509040, 1508993, 1509005, NSF China 61573331, NSF Anhui 1608085QF130, and CAS-XDA06011203
Funding Information:
Work in this paper was supported by NSF 1509040, 1508993, 1509005, NSF China 61573331, NSF Anhui 1608085QF130, and CAS-XDA06011203.
Publisher Copyright:
© 2017 IEEE.
