Channel estimation is a critical task in multiple-input multiple-output (MIMO) digital communications that substantially effects end-to-end system performance. In this work, we introduce a novel approach for channel estimation using deep score-based generative models. A model is trained to estimate the gradient of the logarithm of a distribution and is used to iteratively refine estimates given measurements of a signal. We introduce a framework for training score-based generative models for wireless MIMO channels and performing channel estimation based on posterior sampling at test time. We derive theoretical robustness guarantees for channel estimation with posterior sampling in single-input single-output scenarios, and experimentally verify performance in the MIMO setting. Our results in simulated channels show competitive in-distribution performance, and robust out-of-distribution performance, with gains of up to 5 dB in end-to-end coded communication performance compared to supervised deep learning methods. Simulations on the number of pilots show that high fidelity channel estimation with 25% pilot density is possible for MIMO channel sizes of up to 64 × 256. Complexity analysis reveals that model size can efficiently trade performance for estimation latency, and that the proposed approach is competitive with compressed sensing in terms of floating-point operation (FLOP) count.

Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limited number of measurements, but these methods typically rely on the existence of a large, centralized database of fully sampled scans for training. In this work, we investigate federated learning for MRI reconstruction using end-to-end unrolled deep learning models as a means of training global models across multiple clients (data sites), while keeping individual scans local. We empirically identify a low-data regime across a large number of heterogeneous scans, where a small number of training samples per client are available and non-collaborative models lead to performance drops. In this regime, we investigate the performance of adaptive federated optimization algorithms as a function of client data distribution and communication budget. Experimental results show that adaptive optimization algorithms are well suited for the federated learning of unrolled models, even in a limited-data regime (50 slices per data site), and that client-sided personalization can improve reconstruction quality for clients that did not participate in training.

In recent years, automotive radar has attracted considerable attention due to the growing interest in autonomous driving technologies. Acquiring situational awareness using multimodal data collected at high sampling rates by various sensing devices including cameras, LiDAR, and radar requires considerable power, memory and compute resources which are often limited at an edge device. In this paper, we present a novel adaptive radar sub-sampling algorithm designed to identify regions that require more detailed/accurate reconstruction based on the information about prior environmental conditions, enabling near-optimal performance at considerably lower effective sampling rates. Designed to robustly perform under variable weather conditions, the algorithm was shown on the Oxford radar dataset to achieve accurate scene reconstruction utilizing only 10% of the collected samples in good weather. In the case of the RADIATE dataset acquired during extreme weather conditions (snow, fog), only 20% of the samples were sufficient to enable robust scene reconstruction. A further modification of the algorithm incorporates object motion to enable reliable identification of regions that require attention. This includes monitoring possible future occlusions caused by the objects detected in the present frame. Finally, we train a YOLO network on the RADIATE dataset to perform object detection, obtaining 6.6% AP50 improvement over the baseline Faster R-CNN network.

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems. However, to date this framework has been empirically successful only on certain datasets (for example, human faces and MNIST digits), and it is known to perform poorly on out-of-distribution samples. In this paper, we present the first successful application of the CSGM framework on clinical MRI data. We train a generative prior on brain scans from the fastMRI dataset, and show that posterior sampling via Langevin dynamics achieves high quality reconstructions. Furthermore, our experiments and theory show that posterior sampling is robust to changes in the ground-truth distribution and measurement process. Our code and models are available at: \url{https://github.com/utcsilab/csgm-mri-langevin}.

Forward error correction using soft probability estimates is a central component in modern digital communication receivers and impacts end-to-end system performance. In this work, we introduce EQ-Net: a deep learning approach for joint soft bit estimation (E) and quantization (Q) in high-dimensional multiple-input multiple-output (MIMO) systems. We propose a two-stage algorithm that uses soft bit quantization as pretraining for estimation and is motivated by a theoretical analysis of soft bit representation sizes in MIMO channels. Our experiments demonstrate that a single deep learning model achieves competitive results on both tasks when compared to previous methods, with gains in quantization efficiency as high as $$20\%$$20% and reduced estimation latency by at least $$21\%$$21% compared to other deep learning approaches that achieve the same end-to-end performance. We also demonstrate that the quantization approach is feasible in single-user MIMO scenarios of up to $$64 \times 64$$64×64 and can be used with different soft bit estimation algorithms than the ones during training. We investigate the robustness of the proposed approach and demonstrate that the model is robust to distributional shifts when used for soft bit quantization and is competitive with state-of-the-art deep learning approaches when faced with channel estimation errors in soft bit estimation.