arXiv subjects

Vincent Corlay

Publications and source records attributed to Vincent Corlay.

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

How Many Posterior Samples? Calibrated Stopping for Adaptive Sensing

In classification-oriented adaptive sensing, posterior samples characterize uncertainty at the current measurement state and can serve two roles: they may guide the next sensing direction, while their class labels provide votes for the candidate classes and determine whether sensing should continue. We focus on the stopping layer that turns these votes into a declaration, without modifying the posterior sampler or sensing directions. A natural plug-in rule declares when the observed vote share exceeds a threshold. We show that this threshold is not itself a confidence guarantee: when the underlying vote mass equals the threshold, the plug-in rule declares about half the time. As alternatives, we calibrate a fixed-sample rule and a finite-horizon sequential rule to a prescribed false-declaration probability, and study exact curtailment, which stops a fixed-pool rule once its final verdict is forced. We then derive how one-round declaration probabilities determine posterior-sample cost and classification accuracy along a sensing path. On MNIST with DDRM and a fixed PCA-guided probe sequence, curtailment saves up to 62% of posterior samples. Among the evaluated rules at matched operating points, sequential stopping reduces the cost the most. At a high accuracy, that same sequential rule can trade more posterior samples for fewer measurements.

stat.ML↗

arXiv2026

Classification-oriented adaptive sensing via posterior sampling

Recent advances in diffusion models have enabled high-performance, instance-adaptive compressed sensing through posterior sampling, without task-specific policy training. Existing methods select sensing probes by maximizing total posterior signal variance and are therefore primarily reconstruction-driven. We introduce a classification-driven extension motivated by the closed-form posterior covariance of a class-conditional Gaussian mixture model, which decomposes into within-class and between-class uncertainty. Using calibrated soft classifier outputs, we estimate these uncertainty terms from diffusion posterior samples and propose a classification-oriented criterion for selecting the dominant sensing direction in the unmeasured subspace. Experiments on MNIST and CIFAR-10 compare the resulting classification accuracy, measurement cost, and reconstruction quality with those of reconstruction-oriented counterparts. The results identify regimes in which semantic posterior uncertainty yields a more favorable classification--measurement trade-off and quantify the associated reconstruction cost.

eess.SP↗

arXiv2026

Opportunistic Conditional Entropy Coding with Frozen Analysis and Synthesis Transforms

In many delivery settings, a receiver may already hold a lower-quality or lower-resolution representation of an image, obtained through an independent transmission. Conventional codecs encode a subsequently requested higher-quality representation without exploiting this incidental side information, whereas conditional codecs generally assume a prescribed source of side information that is always available. We instead consider an opportunistic setting in which side information may or may not be present. We introduce a single entropy model that conditions on a previously decoded latent when available and falls back to a standard hyperprior otherwise. The proposed adapter maps the side-information latent to the prior signal required by the entropy model, allowing the same model to support multiple target and side-information quality combinations. The analysis and synthesis transforms remain frozen, enabling retrofitting of an existing learned codec while preserving its latent representation and reconstruction path. When the receiver holds the quality immediately below the target, the proposed method reduces the rate of the subsequent transmission by up to 46%, or by 52% when an additional hyper-latent is transmitted. In the absence of side information, the rate penalty remains below 4%, and the reconstructions are bit-identical across the conditional and fallback modes.

eess.IV↗

arXiv2026

Expected Gain-based Escalation in Vertical Federated Learning

Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to every sample can incur unnecessary communication and computational overhead. This trade-off is particularly relevant in vertical federated learning (VFL), where clients observe different views of the same sample and fusion typically requires transmitting intermediate representations to a server. We study selective escalation in a two-round VFL inference protocol, in which a low-cost first round produces a prediction from client posteriors and a second embedding-fusion round is invoked only when it is expected to improve the final decision. We formulate routing as expected-gain score estimation: a sample is escalated when a predicted improvement in correctness justifies the additional communication. The proposed analytical score combines a calibrated pooled posterior with classwise reliability estimates of the VFL model, both obtained from held-out calibration data, yielding an interpretable router that requires no separately trained routing network. Experiments on multi-view classification benchmarks, including controlled test--time view degradation settings, show that the proposed router improves the communication-accuracy trade-off over confidence-, learned-gain-, and deferral-based baselines.

cs.LG↗

arXiv2026

Adaptive Transform Coding for Semantic Compression

Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for downstream inference. We propose an adaptive transform-coding method for semantic-feature compression motivated by the conditional rate-distortion function of a Gaussian mixture model. The scheme uses mode-dependent transforms and quantizers selected according to the inferred source component, enabling more efficient coding of heterogeneous feature distributions. Evaluations on features from widely used vision backbones and foundation models show that the proposed method outperforms or is competitive with state-of-the-art neural compression methods while preserving flexibility and interpretability.

eess.IV↗

arXiv2026

All LCA models are wrong. Are some of them useful? Towards open computational LCA in ICT

Life Cycle Assessment (LCA) is increasingly used to quantify and regulate the environmental impacts of Information and Communication Technology (ICT) systems. Since direct biosphere measurements are complicated to perform, we claim that the environmental impact assessment of ICT relies heavily on models. In this paper, we first revisit the fundamentals of LCA: we emphasize that ICT LCAs effectively form systems of models, and we argue that such systems require an extra-high level of carefulness in construction, calibration, integration, and interpretation. We then document how this level of rigor is challenging to achieve with current practices. This is illustrated with emblematic examples of model misuse and an analysis of structural challenges related to database choice, scope mismatches, opaque aggregation, and model integration. From this analysis, we derive four key requirements for credible ICT LCA: explicit model lineage, clearly defined model scope, end-to-end traceability, and managed non-obsolescence. Finally, we propose a framework that operationalizes these requirements using explicit dependency graphs, an open and versioned LCA-oriented model repository, automatic enforcement of integrity constraints, and a well-defined model taxonomy.

cs.SE↗

arXiv2026

Model-based Implicit Neural Representation for sub-wavelength Radio Localization

The increasing deployment of large antenna arrays at base stations has significantly improved the spatial resolution and localization accuracy of radio-localization methods. However, traditional signal processing techniques struggle in complex radio environments, particularly in scenarios dominated by non line of sight (NLoS) propagation paths, resulting in degraded localization accuracy. Recent developments in machine learning have facilitated the development of machine learning-assisted localization techniques, enhancing localization accuracy in complex radio environments. However, these methods often involve substantial computational complexity during both the training and inference phases. This work extends the well-established fingerprinting-based localization framework by simultaneously reducing its memory requirements and improving its accuracy. Specifically, a model-based neural network is used to learn the location-to-channel mapping, and then serves as a generative neural channel model. This generative model augments the fingerprinting comparison dictionary while reducing the memory requirements. The proposed method outperforms fingerprinting baselines by achieving sub-wavelength localization accuracy, even in complex static NLoS environments. Remarkably, it offers an improvement by several orders of magnitude in localization accuracy, while simultaneously reducing memory requirements by an order of magnitude compared to classical fingerprinting methods.

eess.SP↗

arXiv2026

Improved Contact Graph Routing in Delay Tolerant Networks with Capacity and Buffer Constraints

Satellite communications present challenging characteristics. Continuous end-to-end connectivity may not be available due to the large distances between satellites. Moreover, resources such as link capacity and buffer memory may be limited. Routing in satellite networks is therefore both complex and crucial to avoid packet losses and long delays. The Delay Tolerant Network (DTN) paradigm has emerged as an efficient solution for managing these challenging networks. Contact Graph Routing (CGR), a deterministic routing algorithm, is one of the most popular DTN algorithms. CGR is compatible with the store, carry, and forward principle, whereby a node receives a message and stores it in its buffer until a transmission opportunity becomes available. However, CGR relies on simplified models to incorporate potential constraints in the route search. For instance, the linear volume assumption is often used to consider capacity constraints. Moreover, capacity management and buffer management are mostly performed during the forwarding phase, once an issue has occurred. These reactive management techniques cause many collisions and increase the average delivery time. In this paper, we propose taking measures before or during the route search in order to find routes that respect both contact-capacity and node-buffer limits. We introduce the contact splitting and edge pruning operations to effectively account for the routing constraints. This ensures that CGR outputs the optimal solution in terms of delivery time among the subset of valid solutions. The problem is formalized as the Feasible Earliest-Arrival Path with Capacity and Buffer constraints (FEAP-CB) and optimality is proved. The proposed approach can also be used to book resources to be used in case of issues during the forwarding phase.

cs.NI↗

arXiv2026

Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding

Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performance must be jointly optimized under resource constraints. While recent works have proposed rate-distortion bounds for coding for machines, these results often rely on strong assumptions on task identifiability and neglect the impact of deployed task models. In this work, we revisit the fundamental limits of single-TOSC through the lens of indirect rate-distortion theory. We highlight the conditions under which existing rate-distortion bounds are achievable and show their limitations in realistic settings. We then introduce task model-aware rate-distortion bounds that account for task model suboptimality and architectural constraints. Experiments on standard classification benchmarks confirm that current learned TOSC schemes operate far from these limits, highlighting transmitter-side complexity as a key bottleneck.

cs.IT↗

arXiv2025

Model-based learning for multi-antenna multi-frequency location-to-channel mapping

Years of study of the propagation channel showed a close relation between a location and the associated communication channel response. The use of a neural network to learn the location-to-channel mapping can therefore be envisioned. The Implicit Neural Representation (INR) literature showed that classical neural architecture are biased towards learning low-frequency content, making the location-to-channel mapping learning a non-trivial problem. Indeed, it is well known that this mapping is a function rapidly varying with the location, on the order of the wavelength. This paper leverages the model-based machine learning paradigm to derive a problem-specific neural architecture from a propagation channel model. The resulting architecture efficiently overcomes the spectral-bias issue. It only learns low-frequency sparse correction terms activating a dictionary of high-frequency components. The proposed architecture is evaluated against classical INR architectures on realistic synthetic data, showing much better accuracy. Its mapping learning performance is explained based on the approximated channel model, highlighting the explainability of the model-based machine learning paradigm.

cs.IT↗

arXiv2025

Physically Parameterized Differentiable MUSIC for DoA Estimation with Uncalibrated Arrays

Direction of arrival (DoA) estimation is a common sensing problem in radar, sonar, audio, and wireless communication systems. It has gained renewed importance with the advent of the integrated sensing and communication paradigm. To fully exploit the potential of such sensing systems, it is crucial to take into account potential hardware impairments that can negatively impact the obtained performance. This study introduces a joint DoA estimation and hardware impairment learning scheme following a model-based approach. Specifically, a differentiable version of the multiple signal classification (MUSIC) algorithm is derived, allowing efficient learning of the considered impairments. The proposed approach supports both supervised and unsupervised learning strategies, showcasing its practical potential. Simulation results indicate that the proposed method successfully learns significant inaccuracies in both antenna locations and complex gains. Additionally, the proposed method outperforms the classical MUSIC algorithm in the DoA estimation task.

eess.SP↗

arXiv2024

CSI Compression using Channel Charting

Reaping the benefits of multi-antenna communication systems in frequency division duplex (FDD) requires channel state information (CSI) reporting from mobile users to the base station (BS). Over the last decades, the amount of CSI to be collected has become very challenging owing to the dramatic increase of the number of antennas at BSs. To mitigate the overhead associated with CSI reporting, compressed CSI techniques have been proposed with the idea of recovering the original CSI at the BS from its compressed version sent by the mobile users. Channel charting is an unsupervised dimensionality reduction method that consists in building a radio-environment map from CSIs. Such a method can be considered in the context of the CSI compression problem, since a chart location is, by definition, a low-dimensional representation of the CSI. In this paper, the performance of channel charting for a task-based CSI compression application is studied. A comparison of the proposed method against baselines on realistic synthetic data is proposed, showing promising results.

cs.IT↗

arXiv2024

Differentiable High-Order Markov Models for Spectrum Prediction

The advent of deep learning and recurrent neural networks revolutionized the field of time-series processing. Therefore, recent research on spectrum prediction has focused on the use of these tools. However, spectrum prediction, which involves forecasting wireless spectrum availability, is an older field where many "classical" tools were considered around the 2010s, such as Markov models. This work revisits high-order Markov models for spectrum prediction in dynamic wireless environments. We introduce a framework to address mismatches between sensing length and model order as well as state-space complexity arising with large order. Furthermore, we extend this Markov framework by enabling fine-tuning of the probability transition matrix through gradient-based supervised learning, offering a hybrid approach that bridges probabilistic modeling and modern machine learning. Simulations on real-world Wi-Fi traffic demonstrate the competitive performance of high-order Markov models compared to deep learning methods, particularly in scenarios with constrained datasets containing outliers.

eess.SP↗

arXiv2024

Fusion of Time and Angle Measurements for Digital-Twin-Aided Probabilistic 3D Positioning

Previous studies explained how the 2D positioning problem in indoor non line-of-sight environments can be addressed using ray tracing with noisy angle of arrival (AoA) measurements. In this work, we generalize these results on two aspects. First, we outline how to adapt the proposed methods to address the 3D positioning problem. Second, we introduce efficient algorithms for data fusion, where propagation-time or relative propagation-time measurements (obtained via e.g., the time difference of arrival) are used in addition to AoA measurements. Simulation results are provided to illustrate the advantages of the approach.

eess.SP↗

arXiv2024

Optimal Sensing Policy With Interference-Model Uncertainty

This paper considers a half-duplex scenario where an interferer behaves according to a parametric model but the values of the model parameters are unknown. We explore the necessary number of sensing steps to gather sufficient knowledge about the interferer's behavior. With more sensing steps, the reliability of the model-parameter estimates is improved, thereby enabling more effective link adaptation. However, in each time slot, the communication system experiencing interference must choose between sensing and communication. Thus, we propose to investigate the optimal policy for maximizing the expected sum communication data rate over a finite-time communication. This approach contrasts with most studies on interference management in the literature, which assume that the parameters of the interference model are perfectly known. We begin by showing that the problem under consideration can be modeled within the framework of a Markov decision process (MDP). Following this, we demonstrate that both the optimal open-loop and optimal closed-loop policies can be determined with reduced computational complexity compared to the standard backward-induction algorithm.

cs.IT↗

arXiv2024

A New Method for the Identification of a Wiener-Hammerstein Model in a Communication Context

We propose a new algorithm to identify a Wiener-Hammerstein system. This model represents a communication channel where two linear filters are separated by a non-linear function modelling an amplifier. The algorithm enables to recover each parameter of the model, namely the two linear filters and the non-linear function. This is to be opposed with estimation algorithms which identify the equivalent Volterra system. The algorithm is composed of three main steps and uses three distinct pilot sequences. The estimation of the parameters is done in the time domain via several instances of the least-square algorithm. However, arguments based on the spectral representation of the signals and filters are used to design the pilot sequences. We also provide an analysis of the proposed algorithm. We estimate, via the theory and simulations, the minimum required size of the pilot sequences to achieve a target mean squared error between the output of the true channel and the output of the estimated model. We obtain that the new method requires reduced-size pilot sequences: The sum of the length of the pilot sequences is approximately the one needed to estimate the convolutional product of the two linear filters with a back-off. A comparison with the Volterra approach is also provided.

cs.IT↗

arXiv2024

Active learning for efficient data selection in radio-signal based positioning via deep learning

We consider the problem of user equipment (UE) positioning based on radio signals via deep learning. As in most supervised-learning tasks, a critical aspect is the availability of a relevant dataset to train a model. However, in a cellular network, the data-collection step may induce a high communication overhead. As a result, to reduce the required size of the dataset, it may be interesting to carefully choose the positions to be labelled and to be used in the training. We therefore propose an active learning approach for efficient data collection. We first show that significant gains (both in terms of positioning accuracy and size of the required dataset) can be obtained for the considered positioning problem using a genie. This validates the interest of active learning for positioning. We then propose a \textcolor{blue}{practical} method to approximate this genie.

cs.IT↗