Learning to Optimize: Training Deep Neural Networks for Interference Management
Top Cited Papers
- 23 August 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 66 (20), 5438-5453
- https://doi.org/10.1109/tsp.2018.2866382
Abstract
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.Keywords
Funding Information
- National Science Foundation (CMMI-1727757, CCF-1526078, CIF-1525194)
- Air Force Office of Scientific Research (15RT0767)
- National Science Foundation (CIF-1525194)
- National Natural Science Foundation of China (61671411, U1709219, 61374020)
- Fundamental Research Funds for the Central Universities
- Zhejiang Provincial NSF of China (LR15F010002)
This publication has 15 references indexed in Scilit:
- Deep architectures for modulation recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Deep learningNature, 2015
- Cross-Layer Provision of Future Cellular Networks: A WMMSE-based approachIEEE Signal Processing Magazine, 2014
- Base Station Activation and Linear Transceiver Design for Optimal Resource Management in Heterogeneous NetworksIEEE Transactions on Signal Processing, 2014
- SCALE: A Low-Complexity Distributed Protocol for Spectrum Balancing in Multiuser DSL NetworksIEEE Transactions on Information Theory, 2009
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Dynamic Spectrum Management: Complexity and DualityIEEE Journal of Selected Topics in Signal Processing, 2008
- Experimental Evaluation of Capacity Statistics for Short VDSL LoopsIEEE Transactions on Communications, 2005
- FDMA capacity of Gaussian multiple-access channels with ISIIEEE Transactions on Communications, 2002
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989