arXiv subjects

Grégoire Danoy

Publications and source records attributed to Grégoire Danoy.

At least 19 recordsLinked to original sources

arXiv2026

TSGuard: A Real-Time Framework for Detecting and Imputing Missing Data in Streaming Time Series

Streaming sensor applications routinely suffer from delayed or missing observations caused by faults, communication losses, or environmental interference. Although recent imputation methods exploit temporal and spatial dependencies effectively, most either assume offline access to future observations or prioritize throughput without enforcing domain plausibility. We present TSGuard, a real-time demonstration system for monitoring, validating, and imputing missing values in streaming time series. TSGuard combines a lightweight graph-aware temporal imputation model with constraint-aware validation, fallback estimation, and operator-facing explanations. Rather than treating imputation as an isolated prediction task, TSGuard integrates it into a broader data-quality loop: detect problematic observations, impute missing values, validate estimated against physical and spatial constraints, and either retain the original value as a plausible anomaly or replace it when it violates domain constraints. Using environmental sensing as a motivating setting, the demo enables users to inspect delayed sensors, compare imputers, define constraints, and validate flagged values in real time. The combination of lightweight online spatiotemporal imputation, domain-aware validation, and explicit retain-or-replace decisions is our central contribution, while interactive explanations make these decisions inspectable and actionable. for operators.

cs.DB↗

arXiv2026

What Does Post-Training Change in Multilingual Reasoning?

Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a complete solution in the user's language, language becomes an access barrier rather than merely a source of performance variation. We audit Qwen3 checkpoints on competition-mathematics tasks in eleven languages. Across the ten non-English languages, only 15.4-17.9% of problems receive a correct, terminating solution with visible reasoning in the requested language in any of 16 samples, compared with 92.9% in English. To identify the source of this disparity, we evaluate thirteen endpoints from one model family, spanning released checkpoints, multilingual supervised fine-tuning (SFT) at two scales, controlled SFT ablations, and three reinforcement-learning (RL) reward formulations. We jointly track correctness, language adherence, termination, and delivery efficiency. The dominant bottleneck shifts across post-training stages. Released models often reason in English. Multilingual SFT restores target-language reasoning, but accuracy declines across multilingual, English-only, and single-language SFT runs, showing that this cost is not specific to multilingual mixing; non-English reasoning traces additionally become prone to non-terminating loops. RL restores termination in both arms at no cost in accuracy, but only the arm whose reward includes a language term delivers: rewarding correctness alone returns the model to English. Together, these stages establish a constructive post-training path from English-pivoted capability to multilingual reasoning that is reliably delivered.

cs.CL↗

arXiv2026

Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training

Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability and memory overhead. Even where a critic is trained, it is discarded once training ends, although it has learned to predict outcomes. We revisit this trend and show that a pretrained critic's ability to predict future outcomes can make it a valuable asset for efficient long-horizon reasoning. First, we find that instability in critic-based RL for long chain-of-thought reasoning is largely an optimization artifact: keeping policy updates small and low in variance restores stable convergence. Second, a well-pretrained critic estimates the posterior probability of eventual success from later trajectory states and unfinished prefixes. Its predictions provide outcome-derived, dense, per-prefix learning signals that, during policy optimization, require neither completed rollouts, step-level annotations, nor external reward labels. Building on this insight, we introduce Reward-Free Policy Optimization (RFPO), which repurposes a single calibrated, frozen critic as a rollout-level reward, a value baseline for generalized advantage estimation, and a success forecaster for unfinished prefixes. We further show that binarizing the debiased score stops the policy from exploiting the critic's length bias. Binarized, RFPO matches supervised PPO without a single label in the training loop, while cutting compute and memory overhead. This makes RFPO well suited to long-horizon reasoning tasks, where outcomes arrive late and generation dominates cost: because rollouts can be rewarded before they finish, training no longer has to pay for waiting on every trajectory to complete. Our findings challenge the prevailing critic-free paradigm and establish critic-based, reward-free optimization as a scalable and computationally efficient path for LLM post-training.

cs.LG↗

arXiv2026

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for a fixed problem class-incurring high pretraining costs and generalizing poorly outside the training distribution. We propose an alternative: a metaheuristic framework that reformulates the randomized constructive phase of GRASP as an online imitation learning task, trained from scratch on each problem instance. A local search procedure acts as an expert oracle, while a decoder-only Transformer serves as the constructive policy. Unlike classical GRASP, which relies on static, myopic heuristic rules based on localized scalar costs, our approach is fully data-driven: the construction policy emerges from high-quality solutions discovered during the search itself, with no problem-specific feature engineering required. We instantiate this as LM-GRASP, a hybrid metaheuristic following an iterative learn-infer-improve cycle, training the policy online via behavioral cloning on a dynamic archive of elite trajectories-no external data or offline pretraining needed. The pipeline interfaces with the domain solely through the objective evaluator used by local search. Evaluated on the Taillard PFSP benchmark (ta51-ta60), the most discriminating block due to half its optima being unknown, LM-GRASP outperforms GPU-GRASP by 28.4 makespan units on average-comparable to the gain from GPU acceleration over sequential execution (27.2 units), though with overlapping standard deviations. This suggests instance-specific, online-trained language models are a promising, practical alternative to hand-engineered constructors, especially for landscapes resistant to classical greedy construction.

cs.LG↗

arXiv2026

SkyHOST: A Unified Architecture for Cross-Cloud Hybrid Object and Stream Transfer

Cloud and big data workloads are increasingly distributing data across multiple cloud providers and regions for rapid decision-making and analytics. Traditional transfer tools are typically specialized for a single paradigm, either stream replication or bulk transfer. This specialization forces users to deploy and manage separate systems with different configurations for each transfer pattern. This paper presents SkyHOST (Hybrid Object and Stream Transfer), a unified data movement architecture built upon the Skyplane framework to bridge the gap between bulk object transfer and streaming workloads through a single control plane and CLI. SkyHOST manages URI-based routing to automatically select the appropriate transfer mechanism, supporting both structured data for record-level ingestion and chunk-based transfer for large binary objects. We demonstrate, through an environmental monitoring use case and empirical evaluation, that SkyHOST provides operational simplicity by consolidating heterogeneous data movement patterns under a single control plane while achieving competitive throughput for cross-region transfers.

cs.DC↗

arXiv2025

A Distance Metric for Mixed Integer Programming Instances

Mixed-integer linear programming (MILP) is a powerful tool for addressing a wide range of real-world problems, but it lacks a clear structure for comparing instances. A reliable similarity metric could establish meaningful relationships between instances, enabling more effective evaluation of instance set heterogeneity and providing better guidance to solvers, particularly when machine learning is involved. Existing similarity metrics often lack precision in identifying instance classes or rely heavily on labeled data, which limits their applicability and generalization. To bridge this gap, this paper introduces the first mathematical distance metric for MILP instances, derived directly from their mathematical formulations. By discretizing right-hand sides, weights, and variables into classes, the proposed metric draws inspiration from the Earth mover's distance to quantify mismatches in weight-variable distributions for constraint comparisons. This approach naturally extends to enable instance-level comparisons. We evaluate both an exact and a greedy variant of our metric under various parameter settings, using the StrIPLIB dataset. Results show that all components of the metric contribute to class identification, and that the greedy version achieves accuracy nearly identical to the exact formulation while being nearly 200 times faster. Compared to state-of-the-art baselines, including feature-based, image-based, and neural network models, our unsupervised method consistently outperforms all non-learned approaches and rivals the performance of a supervised classifier on class and subclass grouping tasks.

cs.LG↗

arXiv2025

Multi-objective methods in Federated Learning: A survey and taxonomy

The Federated Learning paradigm facilitates effective distributed machine learning in settings where training data is decentralized across multiple clients. As the popularity of the strategy grows, increasingly complex real-world problems emerge, many of which require balancing conflicting demands such as fairness, utility, and resource consumption. Recent works have begun to recognise the use of a multi-objective perspective in answer to this challenge. However, this novel approach of combining federated methods with multi-objective optimisation has never been discussed in the broader context of both fields. In this work, we offer a first clear and systematic overview of the different ways the two fields can be integrated. We propose a first taxonomy on the use of multi-objective methods in connection with Federated Learning, providing a targeted survey of the state-of-the-art and proposing unambiguous labels to categorise contributions. Given the developing nature of this field, our taxonomy is designed to provide a solid basis for further research, capturing existing works while anticipating future additions. Finally, we outline open challenges and possible directions for further research.

cs.LG↗

arXiv2025

FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences

Federated Learning (FL) is a distributed machine learning strategy, developed for settings where training data is owned by distributed devices and cannot be shared. FL circumvents this constraint by carrying out model training in distribution. The parameters of these local models are shared intermittently among participants and aggregated to enhance model accuracy. This strategy has been rapidly adopted by the industry in efforts to overcome privacy and resource constraints in model training. However, the application of FL to real-world settings brings additional challenges associated with heterogeneity between participants. Research into mitigating these difficulties in FL has largely focused on only two types of heterogeneity: the unbalanced distribution of training data, and differences in client resources. Yet more types of heterogeneity are becoming relevant as the capability of FL expands to cover more complex problems, from the tuning of LLMs to enabling machine learning on edge devices. In this work, we discuss a novel type of heterogeneity that is likely to become increasingly relevant in future applications: this is preference heterogeneity, emerging when clients learn under multiple objectives, with different importance assigned to each objective on different clients. In this work, we discuss the implications of this type of heterogeneity and propose FedPref, a first algorithm designed to facilitate personalised FL in this setting. We demonstrate the effectiveness of the algorithm across different problems, preference distributions and model architectures. In addition, we introduce a new analytical point of view, based on multi-objective metrics, for evaluating the performance of FL algorithms in this setting beyond the traditional client-focused metrics. We perform a second experimental analysis based in this view, and show that FedPref outperforms compared algorithms.

cs.LG↗

arXiv2025

A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models

Transformer-based models for time series forecasting (TSF) have attracted significant attention in recent years due to their effectiveness and versatility. However, these models often require extensive hyperparameter optimization (HPO) to achieve the best possible performance, and a unified pipeline for HPO in transformer-based TSF remains lacking. In this paper, we present one such pipeline and conduct extensive experiments on several state-of-the-art (SOTA) transformer-based TSF models. These experiments are conducted on standard benchmark datasets to evaluate and compare the performance of different models, generating practical insights and examples. Our pipeline is generalizable beyond transformer-based architectures and can be applied to other SOTA models, such as Mamba and TimeMixer, as demonstrated in our experiments. The goal of this work is to provide valuable guidance to both industry practitioners and academic researchers in efficiently identifying optimal hyperparameters suited to their specific domain applications. The code and complete experimental results are available on GitHub.

cs.LG↗

arXiv2024

Search Strategy Generation for Branch and Bound Using Genetic Programming

Branch-and-Bound (B\&B) is an exact method in integer programming that recursively divides the search space into a tree. During the resolution process, determining the next subproblem to explore within the tree-known as the search strategy-is crucial. Hand-crafted heuristics are commonly used, but none are effective over all problem classes. Recent approaches utilizing neural networks claim to make more intelligent decisions but are computationally expensive. In this paper, we introduce GP2S (Genetic Programming for Search Strategy), a novel machine learning approach that automatically generates a B\&B search strategy heuristic, aiming to make intelligent decisions while being computationally lightweight. We define a policy as a function that evaluates the quality of a B\&B node by combining features from the node and the problem; the search strategy policy is then defined by a best-first search based on this node ranking. The policy space is explored using a genetic programming algorithm, and the policy that achieves the best performance on a training set is selected. We compare our approach with the standard method of the SCIP solver, a recent graph neural network-based method, and handcrafted heuristics. Our first evaluation includes three types of primal hard problems, tested on instances similar to the training set and on larger instances. Our method is at most 2\% slower than the best baseline and consistently outperforms SCIP, achieving an average speedup of 11.3\%. Additionally, GP2S is tested on the MIPLIB 2017 dataset, generating multiple heuristics from different subsets of instances. It exceeds SCIP's average performance in 7 out of 10 cases across 15 times more instances and under a time limit 15 times longer, with some GP2S methods leading on most experiments in terms of the number of feasible solutions or optimality gap.

cs.LG↗

arXiv2024

MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.

cs.MA↗

arXiv2024

Heterogeneity: An Open Challenge for Federated On-board Machine Learning

The design of satellite missions is currently undergoing a paradigm shift from the historical approach of individualised monolithic satellites towards distributed mission configurations, consisting of multiple small satellites. With a rapidly growing number of such satellites now deployed in orbit, each collecting large amounts of data, interest in on-board orbital edge computing is rising. Federated Learning is a promising distributed computing approach in this context, allowing multiple satellites to collaborate efficiently in training on-board machine learning models. Though recent works on the use of Federated Learning in orbital edge computing have focused largely on homogeneous satellite constellations, Federated Learning could also be employed to allow heterogeneous satellites to form ad-hoc collaborations, e.g. in the case of communications satellites operated by different providers. Such an application presents additional challenges to the Federated Learning paradigm, arising largely from the heterogeneity of such a system. In this position paper, we offer a systematic review of these challenges in the context of the cross-provider use case, giving a brief overview of the state-of-the-art for each, and providing an entry point for deeper exploration of each issue.

cs.DC↗

arXiv2024

Training Green AI Models Using Elite Samples

The substantial increase in AI model training has considerable environmental implications, mandating more energy-efficient and sustainable AI practices. On the one hand, data-centric approaches show great potential towards training energy-efficient AI models. On the other hand, instance selection methods demonstrate the capability of training AI models with minimised training sets and negligible performance degradation. Despite the growing interest in both topics, the impact of data-centric training set selection on energy efficiency remains to date unexplored. This paper presents an evolutionary-based sampling framework aimed at (i) identifying elite training samples tailored for datasets and model pairs, (ii) comparing model performance and energy efficiency gains against typical model training practice, and (iii) investigating the feasibility of this framework for fostering sustainable model training practices. To evaluate the proposed framework, we conducted an empirical experiment including 8 commonly used AI classification models and 25 publicly available datasets. The results showcase that by considering 10% elite training samples, the models' performance can show a 50% improvement and remarkable energy savings of 98% compared to the common training practice.

cs.LG↗

arXiv2024

Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework

Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle such an issue, this paper introduces multi-objective reinforcement learning based on decomposition (MORL/D), a novel methodology bridging the literature of RL and MOO. A comprehensive taxonomy for MORL/D is presented, providing a structured foundation for categorizing existing and potential MORL works. The introduced taxonomy is then used to scrutinize MORL research, enhancing clarity and conciseness through well-defined categorization. Moreover, a flexible framework derived from the taxonomy is introduced. This framework accommodates diverse instantiations using tools from both RL and MOO/D. Its versatility is demonstrated by implementing it in different configurations and assessing it on contrasting benchmark problems. Results indicate MORL/D instantiations achieve comparable performance to current state-of-the-art approaches on the studied problems. By presenting the taxonomy and framework, this paper offers a comprehensive perspective and a unified vocabulary for MORL. This not only facilitates the identification of algorithmic contributions but also lays the groundwork for novel research avenues in MORL.

cs.LG↗

arXiv2024

An ARGoS plug-in for the Crazyflie drone

We present a new plug-in for the ARGoS swarm robotic simulator to implement the Crazyflie drone, including its controllers, sensors, and some expansion decks. We have based our development on the former Spiri drone, upgrading the position controller, adding a new speed controller, LED ring, onboard camera, and battery discharge model. We have compared this new plug-in in terms of accuracy and efficiency with data obtained from real Crazyflie drones. All our experiments showed that the proposed plug-in worked well, presenting high levels of accuracy. We believe that this is an important contribution to robot simulations which will extend ARGoS capabilities through the use of our proposed, open-source plug-in.

cs.RO↗

arXiv2023

Constraint Model for the Satellite Image Mosaic Selection Problem

Satellite imagery solutions are widely used to study and monitor different regions of the Earth. However, a single satellite image can cover only a limited area. In cases where a larger area of interest is studied, several images must be stitched together to create a single larger image, called a mosaic, that can cover the area. Today, with the increasing number of satellite images available for commercial use, selecting the images to build the mosaic is challenging, especially when the user wants to optimize one or more parameters, such as the total cost and the cloud coverage percentage in the mosaic. More precisely, for this problem the input is an area of interest, several satellite images intersecting the area, a list of requirements relative to the image and the mosaic, such as cloud coverage percentage, image resolution, and a list of objectives to optimize. We contribute to the constraint and mixed integer lineal programming formulation of this new problem, which we call the \textit{satellite image mosaic selection problem}, which is a multi-objective extension of the polygon cover problem. We propose a dataset of realistic and challenging instances, where the images were captured by the satellite constellations SPOT, Pléiades and Pléiades Neo. We evaluate and compare the two proposed models and show their efficiency for large instances, up to 200 images.

cs.AI↗

arXiv2023

Hyperparameter Optimization for Multi-Objective Reinforcement Learning

Reinforcement learning (RL) has emerged as a powerful approach for tackling complex problems. The recent introduction of multi-objective reinforcement learning (MORL) has further expanded the scope of RL by enabling agents to make trade-offs among multiple objectives. This advancement not only has broadened the range of problems that can be tackled but also created numerous opportunities for exploration and advancement. Yet, the effectiveness of RL agents heavily relies on appropriately setting their hyperparameters. In practice, this task often proves to be challenging, leading to unsuccessful deployments of these techniques in various instances. Hence, prior research has explored hyperparameter optimization in RL to address this concern. This paper presents an initial investigation into the challenge of hyperparameter optimization specifically for MORL. We formalize the problem, highlight its distinctive challenges, and propose a systematic methodology to address it. The proposed methodology is applied to a well-known environment using a state-of-the-art MORL algorithm, and preliminary results are reported. Our findings indicate that the proposed methodology can effectively provide hyperparameter configurations that significantly enhance the performance of MORL agents. Furthermore, this study identifies various future research opportunities to further advance the field of hyperparameter optimization for MORL.

cs.LG↗

arXiv2018

Visualizing the Template of a Chaotic Attractor

Chaotic attractors are solutions of deterministic processes, of which the topology can be described by templates. We consider templates of chaotic attractors bounded by a genus-1 torus described by a linking matrix. This article introduces a novel and unique tool to validate a linking matrix, to optimize the compactness of the corresponding template and to draw this template. The article provides a detailed description of the different validation steps and the extraction of an order of crossings from the linking matrix leading to a template of minimal height. Finally, the drawing process of the template corresponding to the matrix is saved in a Scalable Vector Graphics (SVG) file.

nlin.CD↗