arXiv subjects

Nir Shlezinger

Publications and source records attributed to Nir Shlezinger.

At least 19 recordsLinked to original sources

arXiv2026

Model-based learning for DoA estimation and array calibration via continuous sparse recovery

Direction of arrival (DoA) estimation, a classical signal processing problem, has experienced renewed interest with the advent of integrated sensing and communication (ISAC). While decades of research have yielded highly accurate DoA estimators, hardware impairments have frequently been neglected, despite degrading both DoA estimation accuracy and downstream communication performance in ISAC systems. This work introduces a joint array calibration and DoA estimation method based on the simultaneous orthogonal matching pursuit (SOMP) algorithm, following the model-based machine learning paradigm. The proposed method enables the calibration of antenna arrays subject to severe gain-phase and antenna location impairments through projected gradient descent (PGD), with either supervised or unsupervised objectives. Additionally, DoA estimation is enhanced by extending SOMP to continuous dictionaries via PGD refinement steps. Simulation results demonstrate that the proposed method enables efficient hardware impairment compensation, even without labeled samples, while outperforming conventional sparse recovery and subspace-based DoA estimation baselines.

cs.AI↗

arXiv2026

Array-Agnostic High-Order Ambisonics Encoding via Diffusion Posterior Sampling

Ambisonics provides a device-independent representation of three-dimensional sound fields; however, extracting these coefficients from practical microphone array recordings remains strongly dependent on array geometry, acoustic transfer functions, and spatial sampling resolution. This pipeline is typically divided into two distinct tasks: encoding, which entails reconstructing the physically resolvable spatial components, and upscaling, which requires generating higher-order coefficients. Model-based approaches often fail on irregular arrays due to ill-conditioned transfer matrices, whereas conventional neural encoders remain strictly tied to the specific acquisition setup seen during training. Furthermore, existing upscaling methods usually assume ideal low-order inputs, ignoring device-specific array artifacts. We present ADEUPS, a unified framework that couples an array-independent Ambisonic diffusion prior with an explicit physical acquisition model during inference, enabling zero-shot encoding and upscaling across diverse array configurations. We train our prior using an order-masking strategy and perform inference via score blending, which we demonstrate to be crucial for solving the underlying inverse problem. Through extensive numerical evaluations across various array geometries, we show that ADEUPS consistently outperforms task- and array-specific baselines. Finally, we conduct subjective listening tests to confirm the perceptual effectiveness of our approach.

eess.AS↗

arXiv2026

Deep-Unfolded Penalized MLEM for Rapid Poisson Image Reconstruction

Maximum likelihood expectation maximization (MLEM) is a common approach for Poisson image reconstruction, but accurate recovery requires many iterations and is sensitive to mismatch in the assumed acquisition model. We propose a deep-unfolded penalized MLEM framework that maps a prescribed small number of iterations into trainable layers while retaining the analytical forward/backward projections and the multiplicative structure of MLEM. The unfolded architecture learns layer-dependent regularization and Poisson-model parameters, together with a data-dependent correction of the sensitivity normalization to mitigate model mismatch. We numerically show that our method improves reconstruction resolution at a fixed iteration budget and attains reconstruction quality comparable to long MLEM runs and direct data-driven models.

eess.SP↗

arXiv2026

From Identification to Discovery: Holistic RF Fingerprinting via Learning-Aided Quantization

Radio frequency fingerprint identification (RFFI) enables device identification and authentication by exploiting transmitter-specific hardware impairments embedded in received RF signals. Existing RFFI methods are typically designed for a specific operating regime, such as closed-set identification, open-set recognition (OSR), or discovery of new devices, and often treat these tasks as separate algorithmic components. In this paper, we propose a holistic RFFI framework that jointly supports closed-set identification, OSR, and novel class discovery (NCD) within a single expandable architecture. The proposed method formulates RFFI as vector quantization in a learned latent feature space, where registered devices are represented by labeled codewords. This representation enables closed-set identification through codeword assignment, OSR through uncertainty measures induced by the codebook geometry, and NCD by using the latent representations and open-set uncertainty of rejected samples to organize them into new device identities. We further develop a multi-stage training procedure that combines supervised representation learning, latent-space refinement, codebook initialization, and vector-quantization-aware optimization. Experimental results on LoRa and WiFi RFFI datasets demonstrate that the proposed framework achieves accurate identification of registered devices, reliable detection of unseen transmitters, and effective discovery and registration of new device classes, highlighting the benefits of coupling the different RFFI tasks.

eess.SP↗

arXiv2026

MANET-GNN: Learned Decentralized Optimization of Power Allocation in Multi-Channel MANETs

MANETs enable flexible infrastructure-less wireless connectivity in dynamic and resource-constrained environments. As modern MANETs exploit multiple frequency channels and support heterogeneous traffic patterns, decentralized transmit-power allocation becomes increasingly challenging. We develop a unified learned optimization framework for decentralized power allocation in dynamic multi-hop, multi-channel MANETs. We formulate a constrained end-to-end throughput maximization problem covering unicast, multicast, multicommodity, convergecast, and many-to-many communication. Although centralized and non-convex, this problem serves as an unsupervised training objective for MANET-GNN, a message-passing GNN that operates as a distributed learned optimizer. MANET-GNN uses only local, possibly noisy, CSI and a prescribed number of neighbor message exchanges, enabling low-latency decentralized inference while generalizing across topologies and network sizes. Numerical results show that MANET-GNN achieves centralized-competitive performance across communication frameworks, remains robust to channel uncertainty, and scales effectively across MANET configurations.

cs.LG↗

arXiv2026

Online Learning via Learned Latent Bayesian Tracking

Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are updated sequentially via Bayesian filtering. However, applying Bayesian filters directly to modern deep models is computationally prohibitive due to the high dimensionality of parameter space, forcing existing methods to rely on restrictive approximations or manually designed low-dimensional subspaces. In this work, we identify the absence of a suitable low-dimensional dynamical representation as the core bottleneck in Bayesian filtering-based online learning. Accordingly, we propose Adaptive Update through Representation Adaptation (AURA), a meta-learning framework that learns offline a low-dimensional latent state-space model governing the evolution of optimal model parameters under distribution shift. Online adaptation is then performed via extended Kalman filtering in this learned latent space followed by reconstruction of the full model parameters through a learned lifting map, enabling efficient single-step online adaptation while preserving model expressiveness. Evaluated on online adaptation of neural wireless receivers under time-varying channels and on non-stationary image classification, AURA shows substantial improvements in adaptation speed, accuracy, and computational efficiency over existing online learning and Bayesian filtering baselines, demonstrating that an adaptation-aware latent geometry is beneficial for effective Bayesian online learning in high-dimensional models.

cs.LG↗

arXiv2026

Conformalized Kalman Filters for State Estimation with Trustworthy Confidence Regions

Kalman-type filters are widely used for tracking dynamic systems, yet the confidence regions commonly derived from their estimated covariances can become unreliable under nonlinearities, non-Gaussian disturbances, and model mismatch. In this work, we develop a conformal prediction (CP) framework for equipping Kalman-type filters with statistically reliable confidence regions. Unlike CP applied to black-box estimators, our approach exploits the recursively estimated first- and second-order moments of the state posterior, which capture the time-varying uncertainty induced by the underlying dynamics. Based on these statistical features, we propose three complementary constructions. The first conformally calibrates Gaussian confidence regions induced by the filter moments. The second employs quantile regression to map the estimated moments into the boundaries of adaptive convex regions, which are subsequently calibrated. The third learns a Gaussian-mixture representation of the posterior and conformalizes the resulting density-based regions, enabling the characterization of multimodal and non-convex uncertainty sets. We establish finite- sample coverage guarantees for both sample-wise confidence, which controls miscoverage at individual time instances, and trajectory- wise confidence, which jointly covers the state sequence over a prescribed horizon. Numerical experiments across diverse linear and nonlinear dynamic systems demonstrate that the proposed methods attain the prescribed coverage while producing tight and informative confidence regions, and highlight the relative merits of the three constructions under different posterior characteristics.

eess.SP↗

arXiv2026

Neural Kalman Filtering for Unknown Dynamics: Task-Aware Learning with a Koopman Backbone

Recent years have witnessed a growing interest in AI-aided Kalman filters. While emerging methodologies, such as KalmanNet, were shown to facilitate tracking in partially known state-space models, they are not directly applicable when the underlying dynamics is unknown. To overcome this limitation, we extend the KalmanNet philosophy to the unknown-dynamics regime by developing blind Kalman filtering frameworks that learn both the predictor and the correction gain from data, assuming that the state-evolution function and the noise statistics are both unavailable. To this end, we first introduce a task-aware neural Kalman filtering framework, Blind-KalmanNet, which carries the learning principle of the Kalman gain into the prediction step through a two-head neural architecture that jointly learns a state-dependent linear surrogate and the Kalman gain from data. Building on this formulation, we then develop our main framework, Koopman-aided Blind-KalmanNet, which incorporates Koopman operator theory to lift the unknown dynamics into a latent space where the state evolves linearly. The lifted linear predictor integrates seamlessly into the Blind-KalmanNet structure: the pre-trained deep Koopman network serves as a globally structured predictor, augmented by the task-aware residual surrogate and the learned Kalman gain inherited from Blind-KalmanNet. Extensive experiments demonstrate that the proposed frameworks achieve competitive performance against baselines, with Koopman-aided Blind-KalmanNet attaining the best accuracy across all considered settings.

eess.SP↗

arXiv2026

Generative Learning for Ambisonic Upscaling

Ambisonics Upscaling (AU) aims to enhance the spatial resolution of sound fields by estimating high-order Ambisonics (HOA) components from low-order observations. While deep learning and model-based strategies have been considered for AU, both approaches exhibit significant performance degradation in realistic scenarios, where reverberant sound fields violate the directional sparsity inherent to discriminative mappings. In this work, we address AU as a generative task rather than a deterministic reconstruction, expanding generative modeling to specifically target the recovery of spatial information in reverberant speech. We investigate two dominant continuous-time generative paradigms, adapting both Score-based Generative Model and Flow Matching to these complex acoustic settings. We provide an extensive numerical study comparing our methods against state-of-the-art baselines in various acoustic scenarios. Additionally, we conduct subjective listening tests to evaluate the perceived quality and spatial accuracy of the proposed generative framework across various reverberant scenarios. The studies reveal that Flow Matching consistently outperforms both its discriminative counterparts and Diffusion-based paradigms in all reverberant settings.

eess.AS↗

arXiv2026

AI-Aided ESPRIT for Joint DoA Estimation and Uncertainty Extraction

DoA estimation often requires not only accurate recovery of source directions, but also reliable characterization of the uncertainty in these estimates. While classical subspace methods such as ESPRIT provide principled uncertainty analyses, their performance and uncertainty quantification rely on restrictive assumptions. Recent deep learning approaches alleviate these limitations and enable robust. DoA estimation in challenging conditions, but generally provide point estimates and lack principled uncertainty characterization. In this work, we develop an AI-aided framework for joint DoA estimation and uncertainty quantification that combines the robustness of model-based deep learning with the analytical foundations of classical subspace methods. Building on AI surrogate covariance recovery, we extend existing ESPRIT uncertainty analyses to characterize the full covariance structure of the DoA estimation error and integrate this characterization into a subspace-oriented deep learning architecture. We further propose a dedicated learning strategy that jointly promotes accurate DoA recovery and faithful uncertainty estimation. The resulting methodology preserves the interpretable processing pipeline of classical subspace methods while enabling reliable operation in regimes where conventional approaches struggle. Our numerical studies demonstrate that the proposed framework consistently achieves accurate DoA estimation together with reliable uncertainty characterization across diverse challenging scenarios, including coherent sources, limited snapshots, and array calibration errors.

eess.SP↗

arXiv2026

Array-Agnostic Ambisonics Encoding via Diffusion Posterior Sampling

Spatial audio enhances user immersion by reproducing 3D sound fields, with Ambisonics being a widely adopted representation. While Ambisonics is theoretically independent of the recording setup, practical microphone arrays introduce hardware-dependent encoding artifacts. Moreover, existing data-driven solutions lack flexibility, as they are typically restricted to fixed array geometries. To overcome these limitations, we propose ADEPS, a generative framework that explicitly embeds the physical acquisition model into the inference process. By leveraging this formulation, ADEPS effectively compensates for array-specific distortions while enabling zero-shot encoding across arbitrary array topologies. We train the underlying generative prior in an unsupervised manner solely on target Ambisonic representations. Extensive evaluations across diverse simulated and real microphone arrays demonstrate that ADEPS consistently outperforms both traditional linear and parametric baselines in spatial fidelity and spectral quality.

eess.AS↗

arXiv2026

EM-KalmanNet: Learned Expectation-Maximization for Adaptive Tracking in Partially Known, Block-Wise Time-Varying State-Space Models

State estimation in partially known state space (SS) models is challenging when the dynamics or observation model varies across short data blocks. Classical model-based approaches, such as the expectation-maximization (EM) Kalman filter, jointly recover the latent states and the unknown model parameters, but rely on linear-Gaussian assumptions that should accurately describe the system and require numerous forward-backward passes. Consequently, their performance and computational efficiency may deteriorate under complex and non-stationary real-world conditions. On the other hand, learned Kalman smoothers are robust to model mismatch yet cannot adapt at inference to unseen model variations without labeled data. In this work, we propose EM-KalmanNet, an AI-aided tracking algorithm for adaptive smoothing in blockwise time-varying SS models. The method unfolds a fixed, small number of EM-like iterations into a trainable architecture: a parameter-aware RTSNet implements a learned E-step conditioned on the current model-parameter estimate, while a lightweight M-Net implements a learned M-step that updates the state-transition or the observation matrix using empirical moments, residuals, and gradient-related statistics. The two modules are shared across the unfolded iterations and are trained offline via a dedicated three-stage procedure. During deployment, the per-block parameter estimate is propagated between consecutive blocks, enabling observation-driven adaptation without labeled online data or knowledge of the noise statistics. Experiments involving linear and nonlinear models, Gaussian and non-Gaussian noise, Lorenz attractor tracking, and acoustic source localization demonstrate that EM-KalmanNet consistently outperforms model-based and data-driven benchmarks while substantially reducing inference latency relative to the EM-KF.

eess.SP↗

arXiv2026

Change-Aware Self-Adaptive AI-Aided Kalman Filters With Neural Change Point Detection

Reliable state estimation in dynamical systems is often challenged by model mismatches, unknown noise statistics, and temporal variations. While AI-aided Kalman filters such as KalmanNet leverage deep learning to enhance classical estimation, they remain vulnerable to distribution shifts and lack mechanisms for autonomous adaptation. This work introduces Change-Aware Self-Adaptive KalmanNet (CASA-KalmanNet), an online adaptation framework that integrates a dedicated neural module, termed CPDNet, to monitor the interpretable internal features of KalmanNet and provide soft indicators of reliability degradation. These indicators dynamically regulate an online learning process, enabling data-efficient and timely adaptation to both abrupt and gradual changes in the system without requiring additional state labels from the changed regime. Numerical experiments on linear and nonlinear state-space models show that CASA-KalmanNet consistently outperforms existing learning-based filters under model mismatch, while approaching the accuracy of optimal classical methods with full domain knowledge.

eess.SY↗

arXiv2026

DiffAU: Diffusion-Based Ambisonics Upscaling

Spatial audio enhances immersion by reproducing 3D sound fields, with Ambisonics offering a scalable format for this purpose. While first-order Ambisonics (FOA) notably facilitates hardware-efficient acquisition and storage of sound fields as compared to high-order Ambisonics (HOA), its low spatial resolution limits realism, highlighting the need for Ambisonics upscaling (AU) as an approach for increasing the order of Ambisonics signals. In this work we propose DiffAU, a cascaded AU method that leverages recent developments in diffusion models combined with novel adaptation to spatial audio to generate 3rd order Ambisonics from FOA. By learning data distributions, DiffAU provides a principled approach that rapidly and reliably reproduces HOA in various settings. Experiments in anechoic conditions with multiple speakers, show strong objective and perceptual performance.

eess.AS↗

arXiv2026

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman Filters (KFs) with Deep Neural Networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a latent state in complex and partially known dynamics. However, unlike classic KFs, conventional DNN-based systems do not naturally provide an uncertainty measure, such as error covariance, alongside their estimates, which is crucial in various applications that rely on KF-type tracking. This work bridges this gap by studying error covariance extraction in DNN-aided KFs. We begin by characterizing how uncertainty can be extracted from existing DNN-aided algorithms and distinguishing between approaches by their ability to associate internal features with meaningful KF quantities, such as the Kalman Gain (KG) and prior covariance. We then identify that uncertainty extraction from existing architectures necessitates additional domain knowledge not required for state estimation. Based on this insight, we propose Bayesian KalmanNet, a novel DNN-aided KF that integrates Bayesian deep learning techniques with the recently proposed KalmanNet and transforms the KF into a stochastic machine learning architecture. This architecture employs sampling techniques to predict error covariance reliably without requiring additional domain knowledge, while retaining KalmanNet's ability to accurately track in partially known dynamics. Our numerical study demonstrates that Bayesian KalmanNet provides accurate and reliable tracking in various scenarios representing partially known dynamic systems.

eess.SP↗

arXiv2026

SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

cs.LG↗

arXiv2026

Neural Augmentation of MIMO-OFDM Receivers for Universal LLR Reconstruction

The growing demands for higher throughput and cost-efficient wireless communications drive the need for receivers that are both simple to deploy and robust to hardware impairments and nonlinear environments. While classical model-based receivers and recently proposed deep neural network ( DNN) architectures provide complementary benefits, they either rely on simplified linear Gaussian assumptions, require considerable computational resources, or are tailored for a given setting and modulation. In this work, we propose a compact and modular DNN augmentation that universally refines the soft outputs of existing receivers (model-based or data-driven), addressing two distinct operating regimes: structurally incomplete soft information arising from reduced-complexity detectors, and degraded soft outputs caused by hardware impairments and synchronization errors. A key property of the proposed framework is its task-agnostic nature: operating without any knowledge of the specific source of unreliability, it produces well-calibrated log-likelihood ratios (LLRs) suitable for channel decoding. Our design leverages an element-wise scaled convolutional neural network tailored to perform learned interference cancellation across users and neighboring subcarriers, combined with a training algorithm that encourages accurate LLR s for soft channel decoding. Numerical results demonstrate that the proposed augmentation consistently improves diverse receiver algorithms in challenging channel conditions while incurring minimal overhead.

eess.SP↗

arXiv2026

Online Learning of Modular Bayesian Deep Receivers: Single-Step Adaptation with Streaming Data

Deep neural network (DNN)-based receivers offer a powerful alternative to classical model-based designs for wireless communication, especially in complex and nonlinear propagation environments. However, their adoption is challenged by the rapid variability of wireless channels, which makes pre-trained static DNN-based receivers ineffective, and by the latency and computational burden of online stochastic gradient descent (SGD)-based learning. In this work, we propose an online learning framework that enables rapid low-complexity adaptation of DNN-based receivers. Our approach is based on two main tenets. First, we cast online learning as Bayesian tracking in parameter space, enabling a single-step adaptation, which deviates from multi-epoch SGD . Second, we focus on modular DNN architectures that enable parallel, online, and localized variational Bayesian updates. Simulations with practical communication channels demonstrate that our proposed online learning framework can maintain a low error rate with markedly reduced update latency and increased robustness to channel dynamics as compared to traditional gradient descent based method.

eess.SP↗