Memory-Efficient Distributed Unlearning

Machine unlearning considers the removal of the contribution of a set of data points from a trained model. In a distributed setting, where a server orchestrates training using data available at a set of remote users, unlearning is essential to cope with late-detected malicious or corrupted users. Existing distributed unlearning algorithms require the server to store all model updates observed in training, leading to immense storage overhead for preserving the ability to unlearn. In this work we study lossy compression schemes for facilitating distributed server-side unlearning with limited memory footprint. We propose memory-efficient distributed unlearning (MEDU), a hierarchical lossy compression scheme tailored for server-side unlearning, that integrates user sparsification, differential thresholding, and random lattice coding, to substantially reduce memory footprint. We rigorously analyze MEDU, deriving an upper bound on the difference between the desired model that is trained from scratch and the model unlearned from lossy compressed stored updates. Our bound outperforms the state-of-the-art known bounds for non-compressed decentralized server-side unlearning, even when lossy compression is incorporated. We further provide a numerical study, which shows that suited lossy compression can enable distributed unlearning with notably reduced memory footprint at the server while preserving the utility of the unlearned model.

Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizers

Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-box operation and sensitivity to features learned from data. This work examines the adversarial sensitivity of non-learned decision rules, and particularly of iterative optimizers. Our analysis is inspired by the recent developments in deep unfolding, which cast such optimizers as ML models. We show that non-learned iterative optimizers share the sensitivity to adversarial examples of ML models, and that attacking iterative optimizers effectively alters the optimization objective surface in a manner that modifies the minima sought. We then leverage the ability to cast iteration-limited optimizers as ML models to enhance robustness via adversarial training. For a class of proximal gradient optimizers, we rigorously prove how their learning affects adversarial sensitivity. We numerically back our findings, showing the vulnerability of various optimizers, as well as the robustness induced by unfolding and adversarial training.

Near Field Localization via AI-Aided Subspace Methods

The increasing demands for high-throughput and energy-efficient wireless communications are driving the adoption of extremely large antennas operating at high-frequency bands. In these regimes, multiple users will reside in the radiative near-field, and accurate localization becomes essential. Unlike conventional far-field systems that rely solely on DOA estimation, near-field localization exploits spherical wavefront propagation to recover both DOA and range information. While subspace-based methods, such as MUSIC and its extensions, offer high resolution and interpretability for near-field localization, their performance is significantly impacted by model assumptions, including non-coherent sources, well-calibrated arrays, and a sufficient number of snapshots. To address these limitations, this work proposes AI-aided subspace methods for near-field localization that enhance robustness to real-world challenges. Specifically, we introduce NF-SubspaceNet, a deep learning-augmented 2D MUSIC algorithm that learns a surrogate covariance matrix to improve localization under challenging conditions, and DCD-MUSIC, a cascaded AI-aided approach that decouples angle and range estimation to reduce computational complexity. We further develop a novel model-order-aware training method to accurately estimate the number of sources, that is combined with casting of near field subspace methods as AI models for learning. Extensive simulations demonstrate that the proposed methods outperform classical and existing deep-learning-based localization techniques, providing robust near-field localization even under coherent sources, miscalibrations, and few snapshots.

PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning

Federated learning (FL) enables multiple edge devices to collaboratively train a machine learning model without the need to share potentially private data. Federated learning proceeds through iterative exchanges of model updates, which pose two key challenges: First, the accumulation of privacy leakage over time, and second, communication latency. These two limitations are typically addressed separately: The former via perturbed updates to enhance privacy and the latter using user selection to mitigate latency - both at the expense of accuracy. In this work, we propose a method that jointly addresses the accumulation of privacy leakage and communication latency via active user selection, aiming to improve the trade-off among privacy, latency, and model performance. To achieve this, we construct a reward function that accounts for these three objectives. Building on this reward, we propose a multi-armed bandit (MAB)-based algorithm, termed Privacy-aware Active User SElection (PAUSE) which dynamically selects a subset of users each round while ensuring bounded overall privacy leakage. We establish a theoretical analysis, systematically showing that the reward growth rate of PAUSE follows that of the best-known rate in MAB literature. To address the complexity overhead of active user selection, we propose a simulated annealing-based relaxation of PAUSE and analyze its ability to approximate the reward-maximizing policy under reduced complexity. We numerically validate the privacy leakage, associated improved latency, and accuracy gains of our methods for the federated training in various scenarios.

Optimal ISAC Beamforming Structure and Efficient Algorithms for Sum Rate and CRLB Balancing

Integrated sensing and communications (ISAC) has emerged as a promising paradigm to unify wireless communications and radar sensing, enabling efficient spectrum and hardware utilization. A core challenge with realizing the gains of ISAC stems from the unique challenges of dual purpose beamforming design due to the highly non-convex nature of key performance metrics such as sum rate for communications and the Cramer-Rao lower bound (CRLB) for sensing. In this paper, we propose a low-complexity structured approach to ISAC beamforming optimization to simultaneously enhance spectral efficiency and estimation accuracy. Specifically, we develop a successive convex approximation (SCA) based algorithm which transforms the original non-convex problem into a sequence of convex subproblems ensuring convergence to a locally optimal solution. Furthermore, leveraging the proposed SCA framework and the Lagrange duality, we derive the optimal beamforming structure for CRLB optimization in ISAC systems. Our findings characterize the reduction in radar streams one can employ without affecting performance. This enables a dimensionality reduction that enhances computational efficiency. Numerical simulations validate that our approach achieves comparable or superior performance to the considered benchmarks while requiring much lower computational costs.

Deep Variational Sequential Monte Carlo for High-Dimensional Observations

Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a differentiable particle filter that leverages the unsupervised variational SMC objective to parameterize the proposal and transition distributions with a neural network, designed to learn from high-dimensional observations. Experimental results demonstrate that our approach outperforms established baselines in tracking the challenging Lorenz attractor from high-dimensional and partial observations. Furthermore, an evidence lower bound based evaluation indicates that our method offers a more accurate representation of the posterior distribution.

Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization

A broad range of technologies rely on remote inference, wherein data acquired is conveyed over a communication channel for inference in a remote server. Communication between the participating entities is often carried out over rate-limited channels, necessitating data compression for reducing latency. While deep learning facilitates joint design of the compression mapping along with encoding and inference rules, existing learned compression mechanisms are static, and struggle in adapting their resolution to changes in channel conditions and to dynamic links. To address this, we propose Adaptive Rate Task-Oriented Vector Quantization (ARTOVeQ), a learned compression mechanism that is tailored for remote inference over dynamic links. ARTOVeQ is based on designing nested codebooks along with a learning algorithm employing progressive learning. We show that ARTOVeQ extends to support low-latency inference that is gradually refined via successive refinement principles, and that it enables the simultaneous usage of multiple resolutions when conveying high-dimensional data. Numerical results demonstrate that the proposed scheme yields remote deep inference that operates with multiple rates, supports a broad range of bit budgets, and facilitates rapid inference that gradually improves with more bits exchanged, while approaching the performance of single-rate deep quantization methods.

Deep Unfolding-Empowered MmWave Massive MIMO Joint Communications and Sensing

In this paper, we propose a low-complexity and fast hybrid beamforming design for joint communications and sensing (JCAS) based on deep unfolding. We first derive closed-form expressions for the gradients of the communications sum rate and sensing beampattern error with respect to the analog and digital precoders. Building on this, we develop a deep neural network as an unfolded version of the projected gradient ascent algorithm, which we refer to as UPGANet. This approach efficiently optimizes the communication-sensing performance tradeoff with fast convergence, enabled by the learned step sizes. UPGANet preserves the interpretability and flexibility of the conventional PGA optimizer while enhancing performance through data training. Our simulations show that UPGANet achieves up to a 33.5% higher communications sum rate and 2.5 dB lower beampattern error compared to conventional designs based on successive convex approximation and Riemannian manifold optimization. Additionally, it reduces runtime and computational complexity by up to 65% compared to PGA without unfolding.

AI-Aided Kalman Filters

The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. These methods are used for state estimation of dynamic systems by relying on mathematical representations in the form of simple state-space (SS) models, which may be crude and inaccurate descriptions of the underlying dynamics. Emerging data-centric artificial intelligence (AI) techniques tackle these tasks using deep neural networks (DNNs), which are model-agnostic. Recent developments illustrate the possibility of fusing DNNs with classic Kalman-type filtering, obtaining systems that learn to track in partially known dynamics. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms. We review both generic and dedicated DNN architectures suitable for state estimation, and provide a systematic presentation of techniques for fusing AI tools with KFs and for leveraging partial SS modeling and data, categorizing design approaches into task-oriented and SS model-oriented. The usefulness of each approach in preserving the individual strengths of model-based KFs and data-driven DNNs is investigated in a qualitative and quantitative study, whose code is publicly available, illustrating the gains of hybrid model-based/data-driven designs. We also discuss existing challenges and future research directions that arise from fusing AI and Kalman-type algorithms.

Model-Based Machine Learning for Max-Min Fairness Beamforming Design in JCAS Systems

Joint communications and sensing (JCAS) is expected to be a crucial technology for future wireless systems. This paper investigates beamforming design for a multi-user multi-target JCAS system to ensure fairness and balance between communications and sensing performance. We jointly optimize the transmit and receive beamformers to maximize the weighted sum of the minimum communications rate and sensing mutual information. The formulated problem is highly challenging due to its non-smooth and non-convex nature. To overcome the challenges, we reformulate the problem into an equivalent but more tractable form. We first solve this problem by alternating optimization (AO) and then propose a machine learning algorithm based on the AO approach. Numerical results show that our algorithm scales effectively with the number of the communications users and provides better performance with shorter run time compared to conventional optimization approaches.