arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.09412cs.ITeess.SPmath.IT
收藏

学习优化:训练用于无线资源管理的深度神经网络

Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management

Haoran Sun, Xiangyi Chen, Qingjiang Shi, Mingyi Hong, Xiao Fu, Nicholas D. Sidiropoulos

摘要:

在过去的几十年里,数值优化在解决无线资源管理问题(如功率控制和波束形成器设计)方面发挥了核心作用。然而,优化算法往往带来相当大的复杂性,这造成了理论设计/分析和实时处理之间的严重差距。为了应对这一挑战,我们提出了一种新的基于学习的方法。其关键思想是将资源分配算法的输入和输出视为未知的非线性映射,并使用深度神经网络(DNN)对其进行近似。如果非线性映射可以通过中等规模的DNN准确学习,那么资源分配几乎可以实时的完成-因为通过DNN传递输入只需要少量的简单操作。在这项工作中,我们解决的理论和实践方面的DNN为基础的算法近似与无线资源管理的应用。我们首先确定了一类优化算法,这些算法在理论上可以通过完全连接的DNN“学习”。然后,我们专注于基于DNN的近似的一个流行的功率分配算法命名为WMMSE(石{ \it等} 2011)。我们表明,使用DNN近似WMMSE可以是相当准确的-近似误差$ε$依赖于温和的[在$\log(1/ε)$的顺序]上的神经元和层的DNN的数量。在实现方面,我们使用大量的数值模拟来证明,与基于优化的最先进的功率分配算法相比,DNN可以在计算时间上实现数量级的加速。

英文摘要:

For the past couple of decades, numerical optimization has played a central role in addressing wireless resource management problems such as power control and beamformer design. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. To address this challenge, we propose a new learning-based approach. The key idea is to treat the input and output of a resource allocation algorithm as an unknown non-linear mapping and use a deep neural network (DNN) to approximate it. If the non-linear mapping can be learned accurately by a DNN of moderate size, then resource allocation can be done in almost real time -- since passing the input through a DNN only requires a small number of simple operations. In this work, we address both the thereotical and practical aspects of DNN-based algorithm approximation with applications to wireless resource management. We first pin down a class of optimization algorithms that are `learnable' in theory by a fully connected DNN. Then, we focus on DNN-based approximation to a popular power allocation algorithm named WMMSE (Shi {\it et al} 2011). We show that using a DNN to approximate WMMSE can be fairly accurate -- the approximation error $ε$ depends mildly [in the order of $\log(1/ε)$] on the numbers of neurons and layers of the DNN. On the implementation side, we use extensive numerical simulations to demonstrate that DNNs can achieve orders of magnitude speedup in computational time compared to state-of-the-art power allocation algorithms based on optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑