Following the great success of Machine Learning (ML), especially Deep Neural Networks (DNNs), in many research domains in 2010s, several ML-based approaches were proposed for detection in large inverse linear problems, e.g., massive MIMO systems. The main motivation behind is that the complexity of Maximum A-Posteriori (MAP) detection grows exponentially with system dimensions. Instead of using DNNs, essentially being a black-box, we take a slightly different approach and introduce a probabilistic Continuous relaxation of disCrete variables to MAP detection. Enabling close approximation and continuous optimization, we derive an iterative detection algorithm: Concrete MAP Detection (CMD). Furthermore, extending CMD by the idea of deep unfolding into CMDNet, we allow for (online) optimization of a small number of parameters to different working points while limiting complexity. In contrast to recent DNN-based approaches, we select the optimization criterion and output of CMDNet based on information theory and are thus able to learn approximate probabilities of the individual optimal detector. This is crucial for soft decoding in today's communication systems. Numerical simulation results in MIMO systems reveal CMDNet to feature a promising accuracy complexity trade-off compared to State of the Art. Notably, we demonstrate CMDNet's soft outputs to be reliable for decoders.
翻译:在机器学习(ML),特别是深神经网络(DNN)取得巨大成功之后,2010年代在许多研究领域提出了若干以ML为基础的方法,以探测大型反线性问题,例如大型MIMO系统。其主要动机是,最大A-Posinteri(MAP)的探测复杂性随着系统层面的大小而成倍增长。我们使用DNN(基本上是一个黑箱),而不是采取略微不同的方法,并引入一种稳定地不断放松脱冷变量以用于MAP探测。促成近似和连续优化,我们产生了一种迭代检测算法:具体MAP探测(CCM) 。此外,由于CMDNet的深度发展,我们允许(在线)将少量参数优化到不同的工作点,同时限制复杂性。与最近的DNNN方法相比,我们根据信息理论选择了CMDNet的优化标准和产出,从而能够了解个人最佳探测器的近似概率。这对于软解码的探测算法:具体MAP探测法(CC)探测法(CMD) ;此外,由于CMD(C-Net)的深度发展而将C-MDMD IMF 演示了我们的软化系统,因此,我们能够对C-MDMISISIS IM MAD MAD MAD MAD 的S 的S 的系统进行可靠的模拟结果进行可靠的分析。