Learning the MMSE Channel Estimator
arXiv:1707.05674 · doi:10.1109/TSP.2018.2799164
Abstract
We present a method for estimating conditionally Gaussian random vectors with random covariance matrices, which uses techniques from the field of machine learning. Such models are typical in communication systems, where the covariance matrix of the channel vector depends on random parameters, e.g., angles of propagation paths. If the covariance matrices exhibit certain Toeplitz and shift-invariance structures, the complexity of the MMSE channel estimator can be reduced to O(M log M) floating point operations, where M is the channel dimension. While in the absence of structure the complexity is much higher, we obtain a similarly efficient (but suboptimal) estimator by using the MMSE estimator of the structured model as a blueprint for the architecture of a neural network. This network learns the MMSE estimator for the unstructured model, but only within the given class of estimators that contains the MMSE estimator for the structured model. Numerical simulations with typical spatial channel models demonstrate the generalization properties of the chosen class of estimators to realistic channel models.
To appear in IEEE Transactions on Signal Processing
References in corpus (2)
Cited by in corpus (37)
- Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications
- Mobility-Aware Cooperative Caching in Vehicular Edge Computing Based on Asynchronous Federated and Deep Reinforcement Learning
- Massive MIMO is a Reality -- What is Next? Five Promising Research Directions for Antenna Arrays
- Machine Learning for Wireless Link Quality Estimation: A Survey
- Deep Learning Based Pilot Design for Multi-user Distributed Massive MIMO Systems
- Performance Analysis on Machine Learning-Based Channel Estimation
- A Low Complexity Learning-based Channel Estimation for OFDM Systems with Online Training
- An Asymptotically MSE-Optimal Estimator based on Gaussian Mixture Models
- Deep Learning for Wireless Physical Layer: Opportunities and Challenges
- Machine Learning for MU-MIMO Receive Processing in OFDM Systems
- Variational Autoencoder Leveraged MMSE Channel Estimation
- Leveraging Variational Autoencoders for Parameterized MMSE Estimation
- Channel Estimation based on Gaussian Mixture Models with Structured Covariances
- Towards Optimal Power Control via Ensembling Deep Neural Networks
- Channel Estimation under Hardware Impairments: Bayesian Methods versus Deep Learning
- Spectral Efficiency Analysis of Cell-free Distributed Massive MIMO Systems with Imperfect Covariance Matrix
- CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity
- Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G
- Channel Estimation in Underdetermined Systems Utilizing Variational Autoencoders
- Variational Autoencoder for Channel Estimation: Real-World Measurement Insights
- Intelligent Radio Signal Processing: A Survey
- A Very Brief Introduction to Machine Learning With Applications to Communication Systems
- Blind Coherent Preamble Detection via Neural Networks
- Low-Complex Channel Estimation in Extra-Large Scale MIMO with the Spherical Wave Properties
- Centralized Learning of the Distributed Downlink Channel Estimators in FDD Systems using Uplink Data
- PCA-based Channel Estimation for MIMO Communications
- CSI Clustering with Variational Autoencoding
- A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks
- Deep Learning Based OFDM Channel Estimation Using Frequency-Time Division and Attention Mechanism
- Reproducible Evaluation of Neural Network Based Channel Estimators And Predictors Using A Generic Dataset
- Robust Design of Reconfigurable Intelligent Surfaces for Parameter Estimation in MTC
- Channel Estimation in Massive MIMO under Hardware Non-Linearities: Bayesian Methods versus Deep Learning
- AEVB-Comm: An Intelligent CommunicationSystem based on AEVBs
- Turbo-AI: Iterative Machine Learning Based Channel Estimation for 2D Massive Arrays
- Hybrid Neural/Traditional OFDM Receiver with Learnable Decider
- A Regression Approach to Certain Information Transmission Problems
- A Low-Complexity MIMO Channel Estimator with Implicit Structure of a Convolutional Neural Network