Despite significant advancements in deep learning-based CSI compression, some key limitations remain unaddressed. Current approaches predominantly treat CSI compression as a source-coding problem, thereby neglecting transmission errors. Conventional separate source and channel coding suffers from the cliff effect, leading to significant deterioration in reconstruction performance under challenging channel conditions. While existing autoencoder-based compression schemes can be readily extended to support joint source-channel coding, they struggle to capture complex channel distributions and exhibit poor scalability with increasing parameter count. To overcome these inherent limitations of autoencoder-based approaches, we propose Residual-Diffusion Joint Source-Channel Coding (RD-JSCC), a novel framework that integrates a lightweight autoencoder with a residual diffusion module to iteratively refine CSI reconstruction. Our flexible decoding strategy balances computational efficiency and performance by dynamically switching between low-complexity autoencoder decoding and sophisticated diffusion-based refinement based on channel conditions. Comprehensive simulations demonstrate that RD-JSCC significantly outperforms existing autoencoder-based approaches in challenging wireless environments. Furthermore, RD-JSCC offers several practical features, including a low-latency 2-step diffusion during inference, support for multiple compression rates with a single model, robustness to fixed-bit quantization, and adaptability to imperfect channel estimation.

While neural lossy compression techniques have markedly advanced the efficiency of Channel State Information (CSI) compression and reconstruction for feedback in MIMO communications, efficient algorithms for more challenging and practical tasks—such as CSI compression for future channel prediction and reconstruction with relevant side information—remain underexplored, often resulting in suboptimal performance when existing methods are extended to these scenarios. To that end, we propose a novel framework for compression with side information, featuring an encoding process with fixed-rate compression using a trainable codebook for codeword quantization, and a decoding procedure modeled as a backward diffusion process conditioned on both the codeword and the side information. Experimental results show that our method significantly outperforms existing CSI compression algorithms, often yielding over twofold performance improvement by achieving comparable distortion at less than half the data rate of competing methods in certain scenarios. These findings underscore the potential of diffusion-based compression for practical deployment in communication systems.

Risk-averse modeling is critical in safety-sensitive and high-stakes applications. Conditional Value-at-Risk (CVaR) quantifies such risk by measuring the expected loss in the tail of the loss distribution, and minimizing it provides a principled framework for training robust models. However, direct CVaR minimization remains challenging due to the difficulty of accurately estimating rare, high-loss events—particularly at extreme quantiles. In this work, we propose a novel training framework that synthesizes informative samples for CVaR optimization using score-based generative models. Specifically, we guide a diffusion-based generative model to sample from a reweighted distribution that emphasizes inputs likely to incur high loss under a pretrained reference model. These samples are then incorporated via a loss-weighted importance sampling scheme to reduce noise in stochastic optimization. We establish convergence guarantees and show that the synthesized, high-loss-emphasized dataset substantially contributes to the noise reduction. Empirically, we validate the effectiveness of our approach across multiple settings, including a real-world wireless channel compression task, where our method achieves significant improvements over standard risk minimization strategies.

In modern wireless systems, the feedback of DownLink (DL) Channel State Information (CSI) from User Equipment (UE) to Base Stations (BS) may require substantial computational and feedback bandwidth overheads. A promising approach to improve feedback efficiency is to leverage side information which is correlated to DL CSI. Despite potential of doing so, critical aspects remain underexplored in current research, particularly the quantification of the benefits and the inherent limitations of utilizing side information. This paper addresses these gaps by introducing a novel algorithm to compute the rate-distortion function for general compression scenarios incorporating side information. We apply this algorithm to the DL CSI feedback problem having UL CSI as the side information and generate rate-distortion functions. Using the estimated rate-distortion functions, we measure the gain of side information over diverse feedback rates and UE mobility profiles. The results reveal that the benefits of leveraging side information are particularly significant for UEs characterized by high mobility and constrained to operate at low feedback overheads.

Clustered Federated Learning (CFL) is a promising distributed learning framework that addresses data heterogeneity issues across multiple clients by grouping clients and providing a shared generalized model for each group. However, under privacy-preserving federated learning protocols where there is no direct sharing of clients' local datasets, existing approaches often fail to find optimal client groupings resulting in sub-optimal performance. In this paper, we propose a novel CFL algorithm that achieves robust clustering and learning performance. Conceptually, our algorithm groups clients that exhibit similarity in their model updates by periodically accumulating and clustering the gradients that clients compute for various models. The proposed algorithm is shown to achieve a near-optimal error rate for stochastic convergence to optimal models under mild conditions. We present a detailed analysis of the algorithm along with an evaluation on several CFL benchmarks demonstrating that it outperforms existing approaches in terms of convergence speed, clustering accuracy, and task performance.

There has been growing interest in computing rate-distortion functions for real-world data, as they can provide a theoretical benchmark for compression problems. However, a generalized form of rate-distortion that includes side information and coding for computing has been underexplored, despite its relevance in modern compression problems. To address this gap, we propose a new method for estimating the rate-distortion function for computing with side information, using a Lagrangian framework with neural network-parametrized encoding and decoding strategies. This approach enables targeting specific points on the rate-distortion curve through gradient-based optimization. Our methodology is validated in synthetic environments where rate-distortion functions are known, ensuring accuracy in estimation. Additionally, we extend its application to practical, high-dimensional channel state information compression scenarios. We provide rate-distortion estimation results on these scenarios, which in turn enables us to quantify the usefulness of side information in the practical scenarios.11The code is available at https://github.com/Heasung-Kimlrate-distortion-side-information.

We observe that current Deep Learning (DL)-based Channel State Information (CSI) encoder and decoder architectures achieve a distortion which is highly channel-dependent. To exploit this, we propose a novel learning-based variable-rate coding scheme to reduce overheads associated with CSI feedback. To that end, we propose an architecture which combines (a) training an efficient predictor for the distortion rate tradeoffs achievable for a given channel, and (b) optimization of a decision logic which allocates rates based on the predicted distortion. We evaluate our approach on various wireless channel datasets including the 3GPP 3D channel model and COST2100 with Massive MIMO channel model, and show significant potential reductions of up to 20% in the CSI feedback overhead.

This article considers a power allocation problem in energy harvesting downlink non-orthogonal multiple access (NOMA) systems in which a transmitter sends desired messages to their respective receivers by using harvested energy. To tackle this problem, we make use of a reinforcement learning approach based on a shallow neural network structure. We prove that the optimal power allocation policy and the optimal action-value function depend monotonically on some of their input variables and the shallow neural network structure is designed based on properties revealed in the proof. Different from inefficient deep learning methods that tend to require tremendous computational resources, this structure is capable of fully capturing the characteristics of the desired function with a single hidden layer. The optimized structure also allows learning agents to be robust and highly reliable in learning about randomly occurring data. Furthermore, we provide comprehensive experimental results in harsh environments where various arbitrary factors are assumed in order to demonstrate the robustness of the proposed learning approach compared with deep neural networks without proper grounds. It is also shown that the proposed learning process converges to a policy that outperforms existing power allocation algorithms.

This paper deals with the power allocation problem for achieving the upper bound of sum-rate region in energy harvesting downlink channels. We prove that the optimal power allocation policy that maximizes the sum-rate is an increasing function for harvested energy, channel gains, and remaining battery, regardless of the number of users in the downlink channels. We use this proof as a mathematical basis for the construction of a shallow neural network that can fully reflect the increasing property of the optimal policy. This scheme helps us to avoid using big neural networks which requires huge computational resources and causes overfitting. Through experiments, we reveal the inefficiencies and risks of deep neural network that are not optimized enough for the desired policy, and shows that our approach learns a robust policy even with the severe randomness of environments.

In this paper, we consider a power allocation optimization technique for a time-varying fading broadcast channel in energy harvesting communication systems, in which a transmitter with a rechargeable battery transmits messages to receivers using the harvested energy. We first prove that the optimal online power allocation policy for the sum rate maximization of the transmitter is an increasing function of harvested energy, remaining battery, and each user's channel gain. We then construct an appropriate neural network by relying on increasing behavior of the optimal policy. This two-step approach, by using an effective function approximation as well as providing a fundamental guideline for neural network design, can prevent us from wasting the representational capacity of neural networks. On the basis of the neural network, we apply the policy gradient method to solve the power allocation problem. To validate the performance of our approach, we compare it with the closed-form the optimal policy in a partially observable Markov problem. Through further experiments, it is observed that our online solution achieves a performance close to the theoretical upper bound of the performance in a time-varying fading broadcast channel.

In this paper, we consider a power allocation problem for energy harvesting communication systems, where a transmitter wants to send the desired messages to the receiver with the harvested energy in its rechargeable battery. We propose a new power allocation strategy based on deep reinforcement learning technique to maximize the expected total transmitted data for a given random energy arrival and random channel process. The key idea of our scheme is to lead the transmitter, rather than learning the undesirable power allocation policies, by an action-bounding technique using only causal knowledge of the energy and channel processes. This technique helps traditional reinforcement learning algorithms to work more accurately in the systems, and increases the performance of the learning algorithms. Moreover, we show that the proposed scheme achieves better performance with respect to the expected total transmitted data compared to existing power allocation strategies.

In automotive systems, a radar is a key component of autonomous driving. Using transmit and reflected radar signal by a target, we can capture the target range and velocity. However, when interference signals exist, noise floor increases and it severely affects the detectability of target object. For these reasons, previous studies have been proposed to cancel interference or reconstruct original signals. However, the conventional signal processing methods for canceling the interference or reconstructing the transmits signal are difficult tasks, and also have many restrictions. In this work, we propose a novel approach to mitigate interference using deep learning. The proposed method provides high performance in various interference conditions and has low processing time. Moreover, we show that our proposed method achieves better performance compared to existing signal processing methods.