In this paper, we study a sampling-based detection strategy for massive multiple-input multiple-output (MIMO) systems, driven by a modified discrete diffusion model formulated as an analytical, non-learning sampling process. Built upon this framework, the proposed discrete diffusion-based sampling (DDS) algorithm improves decoding performance by leveraging residual-dependent sampling, compared to the independent randomized successive interference cancellation (SIC). Specifically, the modified diffusion model incorporates a shortcut perturbation toward the SIC solution, a forward diffusion step to enhance diversity, and step-wise alignment with the perturbed received signal. Within this framework, the DDS algorithm further adopts one-dimensional discrete Gaussian distribution, involving a reformulated discrete Gaussian noise and an explicitly characterized sampling range, but retains computational complexity amenable to practical deployment. Moreover, we theoretically demonstrate an improved expected decoding radius over randomized SIC. Finally, simulation results based on massive MIMO detection are presented to confirm performance gain of the proposed DDS algorithm.

The Langevin sampling method relies on an accurate score matching while the existing massive multiple-input multiple output (MIMO) Langevin detection involves an inevitable singular value decomposition (SVD) to calculate the posterior score. In this work, a massive MIMO sampling detection strategy that leverages the denoising diffusion model is proposed to narrow the gap between the given iterative detector and the maximum likelihood (ML) detection in an SVD-free manner. Specifically, the proposed score-based sampling detection strategy, denoted as approximate diffusion detection (ADD), is applicable to a wide range of iterative detection methods, and therefore entails a considerable potential in their performance improvement by multiple sampling attempts. On the other hand, the ADD scheme manages to bypass the channel SVD by introducing a reliable iterative detector to produce a sample from the approximate posterior, so that further Langevin sampling is tractable. Customized by the conjugated gradient descent algorithm as an instance, the proposed sampling scheme outperforms the existing score-based detector in terms of a better complexity-performance trade-off.

Hybrid precoding plays an important role in massive MIMO systems for reducing the hardware cost caused by radio frequency (RF) chains. In this paper, an efficient joint hybrid precoding and analog combining (EJHPAC) scheme is proposed for massive MIMO with multiple-antenna user equipment (UE), which applies the phase elimination method to harvest the power gain. Specifically, the problem of analog combining is transformed to a least square problem with constant modulus constraint. Based on it, we adopt the gradient descent projection (GDP) method to the analog combiner and jointly design the related hybrid precoding algorithm, which leads to the proposed EJHPAC algorithm. According to complexity analysis and simulation results, we show that the EJHPAC algorithm has advantages in both spectral efficiency and computational complexity for massive MIMO systems.

In this paper, the projected-gradient-descent (PGD) -based detector for massive MIMO system, which consists of two basic operations — projection and gradient descent (GD), is studied to achieve the performance improvement. Since the projection and GD step have different loss functions, necessary compromise has to be made to balance them during iterations. For this reason, the generalized PGD (GPGD) method is proposed with flexible choices of projection and GD. Different from performing projection and GD alternatively, we show that implementing projection after every multiple GD steps is a better solution. Meanwhile, the step-size of GD is also investigated for convergence efficiency. After that, by unfolding this proposed GPGD method with deep neural networks (DNN), the self-corrected auto-detector (SAD) is established to achieve better decoding performance, where enhancement by attention mechanism and extension by another iterative method are also given for performance improvement and efficiency.

Deep learning (DL) has emerged as a powerful tool for signal detection in large-scale multiple-input multiple-output (MIMO) systems. In this paper, the recurrent sparse detection network (RS-Net) is proposed for performance improvement and complexity reduction. First of all, in order to reduce complexity, RS-Net unfolds the projected gradient descent (PGD) method in a modified way, which consists of a projection and a gradient descent (GD) part. Meanwhile, an RNN with the parameter-sharing structure is adopted to its projection, which significantly eases the training burden. Then, to improve the detection performance, we regularize RS-Net by introducing sparse representation. Besides, the step size of iterations in GD part is also investigated for better convergence efficiency. Finally, simulations demonstrate a better decoding trade-off between performance and complexity in RS-Net.