Search arXiv⌕ Search

arXiv subjects

Alexandre Benoit

Publications and source records attributed to Alexandre Benoit.

17 recordsLinked to original sources
arXiv2026

Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope

Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well on a related unlabeled target domain. They generally introduce an auxiliary adaptation-related task that can be integrated into the multitask paradigm, which aims to merge multiple single-task models into a unified architecture. In this paper, we propose to associate domain adaptation and multitask balancing in the realistic context of an extreme class imbalance. Therefore, we propose a combined framework to cover and validate these approaches, and evaluate its performance in the physics-based context of the Cherenkov Telescope Array Observatory (CTAO). Along with a comparative study of some relevant adaptation techniques, we highlight the impact of extreme label shift and extend the investigations on importance weighting to rectify it. The complete code and results are published and available as open-source resources on Zenodo.

astro-ph.IM↗
arXiv2026

From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning

Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clients to train a shared-task model collaboratively without exposing their local data. While being a key component in any learning system, data is also a primary source of vulnerabilities and challenges, and a major determinant of a stable and well-converged training. Existing FL reviews describe general foundations, security practices, opportunities, challenges, and applications, without delving into diverse aspects of data and considering problems from the data perspective. They rarely provide a data-lens synthesis that links concrete data properties, split protocols, and defenses to convergence speed and stability. This survey fills that gap with three advances. First, we analyze non-IID into measurable traits and rank their influence on convergence as strong, medium, or light, explaining the mechanisms behind each and reconciling evidence across images, texts, and graphs. Second, we connect experimental splitting practices to the real phenomena they emulate, expose the artifacts they introduce, and show how those artifacts affect target accuracy. Third, we analyze how data-related vulnerabilities and their proposed defenses affect convergence, reporting performance under clean and adversarial conditions to make the convergence-robustness trade-off explicit. To our knowledge, this is the first survey to provide a complete understanding of data-related challenges that govern FL. With clear takeaways distilled for each concern, our work serves as actionable guidance, helping practitioners design their system with predictable convergence and stability.

cs.CR↗
arXiv2026

Fractions of Recurrence Operators for Generalized Fourier Series in Classical Orthogonal Polynomials

We consider series expansions in bases of classical orthogonal polynomials. When such a series solves a linear differential equation with polynomial coefficients, its coefficients satisfy a linear recurrence equation. We interpret this equation as the numerator of a fraction of linear recurrence operators. This interpretation lets us give a simple and unified view of previous algorithms computing these recurrences, with a noncommutative Euclidean algorithm as the algorithmic engine. Finally, we demonstrate the effectiveness of our approach on various examples.

math.CA↗
arXiv2025

Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics

Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inherently alters the graph's structure, raising the risk of distorting important topology-dependent signals. Yet, despite the growing use of rewiring, little is known about which structural properties must be preserved to ensure both performance gains and structural fidelity. In this work, we provide the first systematic analysis of how rewiring affects a range of graph structural metrics, and how these changes relate to downstream task performance. We study seven diverse rewiring strategies and correlate changes in local and global graph properties with node classification accuracy. Our results reveal a consistent pattern: successful rewiring methods tend to preserve local structure while allowing for flexibility in global connectivity. These findings offer new insights into the design of effective rewiring strategies, bridging the gap between graph theory and practical GNN optimization.

cs.LG↗
arXiv2025

Speeding Up MACE: Low-Precision Tricks for Equivarient Force Fields

Machine-learning force fields can deliver accurate molecular dynamics (MD) at high computational cost. For SO(3)-equivariant models such as MACE, there is little systematic evidence on whether reduced-precision arithmetic and GPU-optimized kernels can cut this cost without harming physical fidelity. This thesis aims to make MACE cheaper and faster while preserving accuracy by identifying computational bottlenecks and evaluating low-precision execution policies. We profile MACE end-to-end and per block, compare the e3nn and NVIDIA cuEquivariance backends, and assess FP64/FP32/BF16/FP16 settings (with FP32 accumulation) for inference, short NVT and long NPT water simulations, and toy training runs under reproducible, steady-state timing. cuEquivariance reduces inference latency by about $3\times$. Casting only linear layers to BF16/FP16 within an FP32 model yields roughly 4x additional speedups, while energies and thermodynamic observables in NVT/NPT MD remain within run-to-run variability. Half-precision weights during training degrade force RMSE. Mixing e3nn and cuEq modules without explicit adapters causes representation mismatches. Fused equivariant kernels and mixed-precision inference can substantially accelerate state-of-the-art force fields with negligible impact on downstream MD. A practical policy is to use cuEquivariance with FP32 by default and enable BF16/FP16 for linear layers (keeping FP32 accumulations) for maximum throughput, while training remains in FP32. Further gains are expected on Ampere/Hopper GPUs (TF32/BF16) and from kernel-level FP16/BF16 paths and pipeline fusion.

cs.LG↗
arXiv2025

A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems

This paper introduces a novel hybrid AI method combining H filtering and an adaptive linear neuron network for flicker component estimation in power distribution systems.The proposed method leverages the robustness of the H filter to extract the voltage envelope under uncertain and noisy conditions followed by the use of ADALINE to accurately identify flicker frequencies embedded in the envelope.This synergy enables efficient time domain estimation with rapid convergence and noise resilience addressing key limitations of existing frequency domain approaches.Unlike conventional techniques this hybrid AI model handles complex power disturbances without prior knowledge of noise characteristics or extensive training.To validate the method performance we conduct simulation studies based on IEC Standard 61000 4 15 supported by statistical analysis Monte Carlo simulations and real world data.Results demonstrate superior accuracy robustness and reduced computational load compared to Fast Fourier Transform and Discrete Wavelet Transform based estimators.

eess.SY↗
arXiv2025

Navigating Intelligence: A Survey of Google OR-Tools and Machine Learning for Global Path Planning in Autonomous Vehicles

We offer a new in-depth investigation of global path planning (GPP) for unmanned ground vehicles, an autonomous mining sampling robot named ROMIE. GPP is essential for ROMIE's optimal performance, which is translated into solving the traveling salesman problem, a complex graph theory challenge that is crucial for determining the most effective route to cover all sampling locations in a mining field. This problem is central to enhancing ROMIE's operational efficiency and competitiveness against human labor by optimizing cost and time. The primary aim of this research is to advance GPP by developing, evaluating, and improving a cost-efficient software and web application. We delve into an extensive comparison and analysis of Google operations research (OR)-Tools optimization algorithms. Our study is driven by the goal of applying and testing the limits of OR-Tools capabilities by integrating Reinforcement Learning techniques for the first time. This enables us to compare these methods with OR-Tools, assessing their computational effectiveness and real-world application efficiency. Our analysis seeks to provide insights into the effectiveness and practical application of each technique. Our findings indicate that Q-Learning stands out as the optimal strategy, demonstrating superior efficiency by deviating only 1.2% on average from the optimal solutions across our datasets.

cs.RO↗
arXiv2024

A Multitask Deep Learning Model for Classification and Regression of Hyperspectral Images: Application to the large-scale dataset

Multitask learning is a widely recognized technique in the field of computer vision and deep learning domain. However, it is still a research question in remote sensing, particularly for hyperspectral imaging. Moreover, most of the research in the remote sensing domain focuses on small and single-task-based annotated datasets, which limits the generalizability and scalability of the developed models to more diverse and complex real-world scenarios. Thus, in this study, we propose a multitask deep learning model designed to perform multiple classification and regression tasks simultaneously on hyperspectral images. We validated our approach on a large hyperspectral dataset called TAIGA, which contains 13 forest variables, including three categorical variables and ten continuous variables with different biophysical parameters. We design a sharing encoder and task-specific decoder network to streamline feature learning while allowing each task-specific decoder to focus on the unique aspects of its respective task. Additionally, a dense atrous pyramid pooling layer and attention network were integrated to extract multi-scale contextual information and enable selective information processing by prioritizing task-specific features. Further, we computed multitask loss and optimized its parameters for the proposed framework to improve the model performance and efficiency across diverse tasks. A comprehensive qualitative and quantitative analysis of the results shows that the proposed method significantly outperforms other state-of-the-art methods. We trained our model across 10 seeds/trials to ensure robustness. Our proposed model demonstrates higher mean performance while maintaining lower or equivalent variability. To make the work reproducible, the codes will be available at https://github.com/Koushikey4596/Multitask-Deep-Learning-Model-for-Taiga-datatset.

cs.CV↗
arXiv2024

Deep Learning and IACT: Bridging the gap between Monte-Carlo simulations and LST-1 data using domain adaptation

The Cherenkov Telescope Array Observatory (CTAO) is the next generation of observatories employing the imaging air Cherenkov technique for the study of very high energy gamma rays. The deployment of deep learning methods for the reconstruction of physical attributes of incident particles has evinced promising outcomes when conducted on simulations. However, the transition of this approach to observational data is accompanied by challenges, as deep learning-based models are susceptible to domain shifts. In this paper, we integrate domain adaptation in the physics-based context of the CTAO and shed light on the gain in performance that these techniques bring using LST-1 real acquisitions.

astro-ph.IM↗
arXiv2023

Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope

The Cherenkov Telescope Array is the next generation of observatory using imaging air Cherenkov technique for very-high-energy gamma-ray astronomy. Its first prototype telescope is operational on-site at La Palma and its data acquisitions allowed to detect known sources, study new ones, and to confirm the performance expectations. The application of deep learning for the reconstruction of the incident particle physical properties (energy, direction of arrival and type) have shown promising results when conducted on simulations. Nevertheless, its application to real observational data is challenging because deep-learning-based models can suffer from domain shifts. In the present article, we address this issue by implementing domain adaptation methods into state-of-art deep learning models for Imaging Atmospheric Cherenkov Telescopes event reconstruction to reduce the domain discrepancies, and we shed light on the gain in performance that they bring along.

astro-ph.IM↗
arXiv2021

Analysis of the Cherenkov Telescope Array first Large-Sized Telescope real data using convolutional neural networks

The Cherenkov Telescope Array (CTA) is the future ground-based gamma-ray observatory and will be composed of two arrays of imaging atmospheric Cherenkov telescopes (IACTs) located in the Northern and Southern hemispheres respectively. The first CTA prototype telescope built on-site, the Large-Sized Telescope (LST-1), is under commissioning in La Palma and has already taken data on numerous known sources. IACTs detect the faint flash of Cherenkov light indirectly produced after a very energetic gamma-ray photon has interacted with the atmosphere and generated an atmospheric shower. Reconstruction of the characteristics of the primary photons is usually done using a parameterization up to the third order of the light distribution of the images. In order to go beyond this classical method, new approaches are being developed using state-of-the-art methods based on convolutional neural networks (CNN) to reconstruct the properties of each event (incoming direction, energy and particle type) directly from the telescope images. While promising, these methods are notoriously difficult to apply to real data due to differences (such as different levels of night sky background) between Monte Carlo (MC) data used to train the network and real data. The GammaLearn project, based on these CNN approaches, has already shown an increase in sensitivity on MC simulations for LST-1 as well as a lower energy threshold. This work applies the GammaLearn network to real data acquired by LST-1 and compares the results to the classical approach that uses random forests trained on extracted image parameters. The improvements on the background rejection, event direction, and energy reconstruction are discussed in this contribution.

astro-ph.IM↗
arXiv2021

First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning

The Cherenkov Telescope Array is the future of ground-based gamma-ray astronomy. Its first prototype telescope built on-site, the Large Size Telescope 1, is currently under commissioning and taking its first scientific data. In this paper, we present for the first time the development of a full-event reconstruction based on deep convolutional neural networks and its application to real data. We show that it outperforms the standard analysis, both on simulated and on real data, thus validating the deep approach for the CTA data analysis. This work also illustrates the difficulty of moving from simulated data to actual data.

astro-ph.IM↗
arXiv2017

Deep Learning for automatic sale receipt understanding

As a general rule, data analytics are now mandatory for companies. Scanned document analysis brings additional challenges introduced by paper damages and scanning quality.In an industrial context, this work focuses on the automatic understanding of sale receipts which enable access to essential and accurate consumption statistics. Given an image acquired with a smart-phone, the proposed work mainly focuses on the first steps of the full tool chain which aims at providing essential information such as the store brand, purchased products and related prices with the highest possible confidence. To get this high confidence level, even if scanning is not perfectly controlled, we propose a double check processing tool-chain using Deep Convolutional Neural Networks (DCNNs) on one hand and more classical image and text processings on another hand.The originality of this work relates in this double check processing and in the joint use of DCNNs for different applications and text analysis.

cs.CV↗
arXiv2014

Rigorous uniform approximation of D-finite functions using Chebyshev expansions

A wide range of numerical methods exists for computing polynomial approximations of solutions of ordinary differential equations based on Chebyshev series expansions or Chebyshev interpolation polynomials. We consider the application of such methods in the context of rigorous computing (where we need guarantees on the accuracy of the result), and from the complexity point of view. It is well-known that the order-n truncation of the Chebyshev expansion of a function over a given interval is a near-best uniform polynomial approximation of the function on that interval. In the case of solutions of linear differential equations with polynomial coefficients, the coefficients of the expansions obey linear recurrence relations with polynomial coefficients. Unfortunately, these recurrences do not lend themselves to a direct recursive computation of the coefficients, owing among other things to a lack of initial conditions. We show how they can nevertheless be used, as part of a validated process, to compute good uniform approximations of D-finite functions together with rigorous error bounds, and we study the complexity of the resulting algorithms. Our approach is based on a new view of a classical numerical method going back to Clenshaw, combined with a functional enclosure method.

cs.SC↗
arXiv2009

Chebyshev Expansions for Solutions of Linear Differential Equations

A Chebyshev expansion is a series in the basis of Chebyshev polynomials of the first kind. When such a series solves a linear differential equation, its coefficients satisfy a linear recurrence equation. We interpret this equation as the numerator of a fraction of linear recurrence operators. This interpretation lets us give a simple view of previous algorithms, analyze their complexity, and design a faster one for large orders.

cs.SC↗
arXiv2008

Sign Language Tutoring Tool

In this project, we have developed a sign language tutor that lets users learn isolated signs by watching recorded videos and by trying the same signs. The system records the user's video and analyses it. If the sign is recognized, both verbal and animated feedback is given to the user. The system is able to recognize complex signs that involve both hand gestures and head movements and expressions. Our performance tests yield a 99% recognition rate on signs involving only manual gestures and 85% recognition rate on signs that involve both manual and non manual components, such as head movement and facial expressions.

cs.LG↗