The introduction of massive MIMO (Multiple Input Multiple Output) communication systems enables base stations (BS) to perform beamforming for enhancing communication reliability. A typical key assumption, however, is the availability of accurate downlink channel state information (CSI). In practice, CSI estimation and reporting delays coupled with the process of channel aging result in the BS receiving outdated CSI information, which in turn impacts the system's spectral efficiency. To combat this latency, this paper develops efficient methods of CSI prediction that preemptively predict future downlink CSI based on historical data. We leverage the spatial and temporal correlation properties of the channel and use explicit feature extraction frameworks for both dimensions to accurately predict future CSI. We analyze combinations of spatial and temporal feature extractors in terms of a tradeoff between performance and latency. We evaluate the performance of the proposed prediction model in terms of proximity to the ground truth, prediction latency, and model footprint. Our experiments show that our method outperforms classical statistical methods as well as existing CSI prediction baselines.

In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resource-intensive to produce. To this end, the generation of realistic wireless channels plays a key role in the subsequent design of effective ML algorithms for wireless communication systems. Generative models have been proposed to synthesize channel matrices, but outputs produced by such methods may not correspond to geometrically viable channels and do not provide any insight into the scenario being generated. In this work, we aim to address both these issues by integrating established parametric, physics-based geometric channel (PPGC) modeling frameworks with generative methods to produce realistic channel matrices with interpretable representations in the parameter domain. We show that the generative model converges to prohibitively suboptimal stationary points when learning the underlying prior directly over the parameters due to the non-convex PPGC model. To address this limitation, we propose a linearized reformulation of the problem to ensure smooth gradient flow during generative model training, while also providing insights into the underlying physical environment. We evaluate our model against prior baselines by comparing the generated, scenario-specific samples in terms of the 2-Wasserstein distance and through its utility when used for downstream compression tasks.

In this work, we propose a deep learning approach for jointly compressing and denoising the CSI feedback in massive MIMO systems. We consider a practical scenario where only noisy CSI is available for training and inference. To jointly denoise and compress the CSI feedback for improved reconstruction quality without having access to true CSI, we propose a novel generic loss function based on the Stein's unbiased risk estimator (SURE) for unsupervised denoising, and the evidence lower bound (ELBO) for CSI compression. This is in contrast to most existing supervised denoising methods that either require knowledge of the true CSI or are limited to high SNR regimes. Empirically, we show that the proposed approach improves the reconstruction quality of the state-of-the-art method. Moreover, the proposed approach is independent of the choice of the encoder-decoder architecture and can be easily extended to the existing volume of work on this topic.

To compensate for the path losses in millimeter wave (mmWave) communication, multiple-input-multiple-output (MIMO) systems leverage beamforming-based solutions to boost the received SNR. Since beamforming requires knowledge of the wireless channel, its performance is also closely tied with the channel estimation accuracy. In mmWave communication, wireless channels are known to have only a few dominant paths. Several channel estimation methods leverage this characteristic by either using low-rank methods or by modeling element-wise sparsity of channels in angular domain. In this work we propose that the channel in angular domain is better characterized as group sparse rather than element-wise sparse. We further leverage the recent advancements in implicit regularization with gradient descent to develop a non-convex formulation that implicitly enforces group sparsity without additional regularization terms. We further compare the performance of the proposed approach against existing low rank or sparsity based matrix completion methods for channel estimation.

Hybrid beamforming has evolved as a promising technology that offers the balance between system performance and design complexity in mmWave MIMO systems. Existing hybrid beamforming methods either impose unit-modulus constraints or a codebook constraint on the analog precoders/combiners, which in turn results in a performance-overhead tradeoff. This paper puts forth a tensor framework to handle the wideband hybrid beamforming problem, with Vandermonde constraints on the analog precoders/combiners. The proposed method strikes the balance between performance, overhead and complexity. Numerical results on a 3GPP link-level test bench reveal the efficacy of the proposed approach relative to the codebook-based method while attaining the same feedback overhead. Moreover, the proposed method is shown to achieve comparable performance to the unit-modulus approaches, with substantial reductions in overhead.

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that utilizes forward wavelet transforms to decompose the input signal by spatial frequency. Our encoder generates separate bitstreams for each latent representation of low and high frequencies. This enables our decoder to selectively decode bitstreams in a quality-scalable manner. Hence, the decoder can produce an enhanced image by using an enhancement bitstream in addition to the base bitstream. Furthermore, our method is able to enhance only a specific region of interest (ROI) by using a corresponding part of the enhancement latent representation. Our experiments demonstrate that the proposed method shows competitive rate-distortion performance compared to several non-scalable image codecs. We also showcase the effectiveness of our two-level quality scalability, as well as its practicality in ROI quality enhancement.

Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The NNR standard contains compression-efficient quantization and deep context-adaptive binary arithmetic coding (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies. This paper provides an overview of the technical features and characteristics of NNR.

Deep neural networks (DNNs), despite their performance on a wide variety of tasks, are still out of reach for many applications as they require significant computational resources. In this paper, we present a low-rank based end-to-end deep neural network compression framework with the goal of enabling DNNs performance to computationally constrained devices. The proposed framework includes techniques for low-rank based structural approximation, quantization and lossless arithmetic coding. Many of these techniques have been accepted in the MPEG working draft on compressed Neural Network Representations. We demonstrate the efficacy of the proposed framework via extensive experiments on a variety of DNNs for various tasks considered in this standardization activity. These techniques provide impressive performance on DNNs used in ImageNet Large-Scale Visual Recognition Challenge by compressing VGG16 by 61x, ResNet50 by almost 15x, and MobileNetV2 by almost 7x.

In this paper, we propose MCformer - a novel deep neural network for the automatic modulation classification task of complex-valued raw radio signals. MCformer architecture leverages convolution layer along with self-attention based encoder layers to efficiently exploit temporal correlation between the embeddings produced by convolution layer. MCformer provides state of the art classification accuracy at all signal-to-noise ratios in the RadioML2016.10b data-set with significantly less number of parameters which is critical for fast and energy-efficient operation.

An infrastructure-less indoor localization system is proposed based on fingerprints of light signals acquired at high frequencies. In contrast to other systems that modulate lights, the proposed system distinguishes lights by learning from training samples. Due to slight differences in the electronic components used in the construction of compact fluorescent light (CFL) and light emitting diode (LED) bulbs, the optical signals emitted by each light bulb have slight differences with other light bulbs even within the same brand and model. Light signals are digitized with a fast and accurate analog-to-digital converter (ADC) at up to 1 mega-samples/second, segmented, and mapped into the frequency domain using the Fast Fourier Transform (FFT). Spectral features based on the FFT are filtered, normalized, and used as training data for supervised machine learning algorithms. Results are provided for two classifiers of varying complexity: (1) A k-Nearest Neighbor (KNN) classifier; (2) A Convolutional Neural Net (CNN) classifier. A hardware system for indoor localization was designed to analyze the performance of the classifiers. Under certain restrictions, results show that light bulbs may be identified with high accuracy without special infrastructure for modulation. Identifying a light bulb is meant to be synonymous with identifying its associated location.