TY - JOUR
T1 - Learning to Optimize
T2 - Training Deep Neural Networks for Interference Management
AU - Sun, Haoran
AU - Chen, Xiangyi
AU - Shi, Qingjiang
AU - Hong, Mingyi
AU - Fu, Xiao
AU - Sidiropoulos, Nicholas D.
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2018/10/15
Y1 - 2018/10/15
N2 - Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as communications, radar, filter design, and speech and image analytics, just to name a few. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. In this paper, we aim at providing a new learning-based perspective to address this challenging issue. The key idea is to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it. If the nonlinear mapping can be learned accurately by a DNN of moderate size, then SP tasks can be performed effectively-since passing the input through a DNN only requires a small number of simple operations. In our paper, we first identify a class of optimization algorithms that can be accurately approximated by a fully connected DNN. Second, to demonstrate the effectiveness of the proposed approach, we apply it to approximate a popular interference management algorithm, namely, the WMMSE algorithm. Extensive experiments using both synthetically generated wireless channel data and real DSL channel data have been conducted. It is shown that, in practice, only a small network is sufficient to obtain high approximation accuracy, and DNNs can achieve orders of magnitude speedup in computational time compared to the state-of-the-art interference management algorithm.
AB - Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as communications, radar, filter design, and speech and image analytics, just to name a few. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. In this paper, we aim at providing a new learning-based perspective to address this challenging issue. The key idea is to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it. If the nonlinear mapping can be learned accurately by a DNN of moderate size, then SP tasks can be performed effectively-since passing the input through a DNN only requires a small number of simple operations. In our paper, we first identify a class of optimization algorithms that can be accurately approximated by a fully connected DNN. Second, to demonstrate the effectiveness of the proposed approach, we apply it to approximate a popular interference management algorithm, namely, the WMMSE algorithm. Extensive experiments using both synthetically generated wireless channel data and real DSL channel data have been conducted. It is shown that, in practice, only a small network is sufficient to obtain high approximation accuracy, and DNNs can achieve orders of magnitude speedup in computational time compared to the state-of-the-art interference management algorithm.
KW - Optimization algorithms approximation
KW - WMMSE algorithm
KW - deep neural networks
KW - interference management
UR - http://www.scopus.com/inward/record.url?scp=85052686714&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052686714&partnerID=8YFLogxK
U2 - 10.1109/TSP.2018.2866382
DO - 10.1109/TSP.2018.2866382
M3 - Article
AN - SCOPUS:85052686714
SN - 1053-587X
VL - 66
SP - 5438
EP - 5453
JO - IEEE Transactions on Signal Processing
JF - IEEE Transactions on Signal Processing
IS - 20
M1 - 8444648
ER -