Portail HAL de Télécom Paris
Not a member yet
14191 research outputs found
Sort by
Conséquences de l’entrée en application du Data Act dans le secteur automobile
No full textInternational audienceCet article fait partie d'un dossier sur les enjeux juridiques et de cybersécurité dans le secteur automobile. Il introduit les principaux changements induits par l'entrée en application du règlement européen sur les données, en adoptant une approche sectorielle. Sont présentés les conséquences spécifiques dans le secteur automobile, les démarches à réaliser pour se mettre en conformité, son articulation avec d'autres règlementations sectorielles comme l'UN R156 ou la directive ITS, ainsi que les récentes lignes directrices de la Commission européenne sur l'application du règlement aux données issues des véhicules connectés
Efficient learning of bosonic Gaussian unitaries
No full textBosonic Gaussian unitaries are fundamental building blocks of central continuous-variable quantum technologies such as quantum-optic interferometry and bosonic error-correction schemes. In this work, we present the first time-efficient algorithm for learning bosonic Gaussian unitaries with a rigorous analysis. Our algorithm produces an estimate of the unknown unitary that is accurate to small worst-case error, measured by the physically motivated energy-constrained diamond distance. Its runtime and query complexity scale polynomially with the number of modes, the inverse target accuracy, and natural energy parameters quantifying the allowed input energy and the unitary's output-energy growth.The protocol uses only experimentally friendly photonic resources-coherent and squeezed probes, passive linear optics, and heterodyne/homodyne detection. We then employ an efficient classical post-processing routine that leverages a symplectic regularization step to project matrix estimates onto the symplectic group. In the limit of unbounded input energy, our procedure attains arbitrarily high precision using only 2m + 2 queries, where m is the number of modes. To our knowledge, this is the first provably efficient learning algorithm for a multiparameter family of continuous-variable unitaries.</p
On Gossip Algorithms for Machine Learning with Pairwise Objectives
No full textInternational audienceIn the IoT era, information is more and more frequently picked up by connected smart sensors with increasing, though limited, storage, communication and computation abilities. Whether due to privacy constraints or to the structure of the distributed system, the development of statistical learning methods dedicated to data that are shared over a network is now a major issue. Gossip-based algorithms have been developed for the purpose of solving a wide variety of statistical learning tasks, ranging from data aggregation over sensor networks to decentralized multi-agent optimization. Whereas the vast majority of contributions consider situations where the function to be estimated or optimized is a basic average of individual observations, it is the goal of this article to investigate the case where the latter is of pairwise nature, taking the form of a U -statistic of degree two. Motivated by various problems such as similarity learning, ranking or clustering for instance, we revisit gossip algorithms specifically designed for pairwise objective functions and provide a comprehensive theoretical framework for their convergence. This analysis fills a gap in the literature by establishing conditions under which these methods succeed, and by identifying the graph properties that critically affect their efficiency. In particular, a refined analysis of the convergence upper and lower bounds is performed
Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation
No full textInternational audienceThe emergence of Large Language Models (LLMs) presents a dual challenge in the fight against disinformation. These powerful tools, capable of generating human-like text at scale, can be weaponised to produce sophisticated disinformation, yet they also hold promise for enhancing mitigation strategies. This paper investigates the complex dynamics between LLMs and disinformation in small, localised settings through a communication game based on online forums, inspired by Werewolf, with 25 participants. We analyse how Disinformers, Moderators, and Users leverage LLMs to advance their goals, revealing both the potential for misuse and combating disinformation. Our findings highlight the varying uses of LLMs depending on the participants' roles and strategies, underscoring the importance of understanding their effectiveness in this context. We conclude by discussing implications for future LLM development and online platform design, advocating for a balanced approach that empowers users and fosters trust while mitigating the risks of LLM-assisted disinformation
Of All StrIPEs: Investigating Structure-informed Positional Encoding for Efficient Music Generation
No full textWhile music remains a challenging domain for generative models like Transformers, a two-pronged approach has recently proved successful: inserting musically-relevant structural information into the positional encoding (PE) module and using kernel approximation techniques based on Random Fourier Features (RFF) to lower the computational cost from quadratic to linear. Yet, it is not clear how such RFF-based efficient PEs compare with those based on rotation matrices, such as Rotary Positional Encoding (RoPE). In this paper, we present a unified framework based on kernel methods to analyze both families of efficient PEs. We use this framework to develop a novel PE method called RoPEPool, capable of extracting causal relationships from temporal sequences. Using RFF-based PEs and rotation-based PEs, we demonstrate how seemingly disparate PEs can be jointly studied by considering the interactions they induce between two descriptive levels of the data: the input, capturing quickly-varying components, and the prior, capturing slowly-varying components. For empirical validation, we use a symbolic music generation task, namely, melody harmonization. We show that RoPEPool, combined with highly-informative structural priors, outperforms all methods
Exploiting Subgradient Sparsity in Max-Plus Neural Networks
No full textDeep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Max-Plus neural architecture in which classical addition and multiplication are replaced with maximum and summation operations respectively. This is a promising architecture in terms of interpretability, but its training is challenging. A particular feature is that this algebraic structure naturally induces sparsity in the subgradients, as only neurons that contribute to the maximum affect the loss. However, standard backpropagation fails to exploit this sparsity, leading to unnecessary computations. In this work, we focus on the minimization of the worst sample loss which transfers this sparsity to the optimization loss. To address this, we propose a sparse subgradient algorithm that explicitly exploits the algebraic sparsity. By tailoring the optimization procedure to the non-smooth nature of Max-Plus models, our method achieves more efficient updates while retaining theoretical guarantees. This highlights a principled path toward bridging algebraic structure and scalable learning
Characterization of EMF exposure induced by French cellular networks
No full textInternational audienceAbstract This study presents a comprehensive evaluation of electromagnetic exposure in operational French fourth generation (4 G)/long term evolution (LTE) networks, combining field measurements with computational modeling to assess both uplink (UL) and downlink (DL) contributions. We introduce the novel Radiated Energy per Bit Transmitted (REBT) metric to quantify network radiated energy efficiency, while characterizing TX power patterns across different services, revealing higher mean-to-maximum power ratios for data services compared to voice calls. Through analysis of a representative 2600 MHz user, we demonstrate field-strength-dependent exposure dynamics: with DL field strength of 1 V/m, UL contributes 30% (head) and 12.8% (whole body) of total exposure, while at 0.38 V/m, UL becomes predominant (75% head, 50.4% whole body). Notably, the relative contribution of UL exposure to the total head exposure is consistently higher than that of DL exposure across all scenarios. All measured exposure levels remain well below ICNIRP safety limits, validating safety compliance of LTE. The study establishes an important methodological framework, combining the global exposure index with detailed transfer function analysis, providing critical insights for both current 4 G and emerging fifth generation (5 G) exposure assessments
Unrolled Multiplicative Updates for Nonnegative Matrix Factorization applied to Hyperspectral Unmixing
No full textHyperSpectral Unmixing (HSU), the problem of separating mixed spectra of overlapping materials in a hyperspectral image, has motivated dedicated algorithmic developments in the last two decades. On the one hand, traditional model-based algorithms frequently guarantee interpretable results. On the other hand, deep-learning-based approaches are often faster at inference time and may obtain better empirical results. This work utilizes the strengths of both approaches by building on the deep unrolling paradigm. Our contribution is twofold. First, we propose two new algorithms based on deep unrolling of the well-known Multiplicative Updates. The first, coined Non-Adaptive Learned Multiplicative Updates (NALMU), adopts a simple element-wise multiplicative scheme. The second, called Recursive Adaptive Learned Multiplicative Updates (RALMU), has more flexible updates and better take into account the spatial correlations in the abundances. Second, we relate NALMU to the minimization of an explicit cost function under some assumptions. Such guarantees are unique in the HSU field. NALMU and RALMU are tested on astrophysics and remote sensing datasets. They outperform the other deep learning-based HSU algorithms and classical iterative schemes for the endmember estimates and obtain competitive results for the abundance estimates, even when trained in a self-supervised way. The code used in this paper will be made available upon publication
Capsule networks do not need to model everything
No full textInternational audienceCapsule networks are biologically inspired neural networks that group neurons into vectors called capsules, each explicitly representing an object or one of its parts. The routing mechanism connects capsules in consecutive layers, forming a hierarchical structure between parts and objects, also known as a parse tree. Capsule networks often attempt to model all elements in an image, requiring large network sizes to handle complexities such as intricate backgrounds or irrelevant objects. However, this comprehensive modeling leads to increased parameter counts and computational inefficiencies. Our goal is to enable capsule networks to focus only on the object of interest, reducing the number of parse trees. We accomplish this with REM (Routing Entropy Minimization), a technique that minimizes the entropy of the parse tree-like structure. REM drives the model parameters distribution towards low entropy configurations through a pruning mechanism, significantly reducing the generation of intra-class parse trees. This empowers capsules to learn more stable and succinct representations with fewer parameters and negligible performance loss
