Cité de l’Économie et des Métiers de Demain Cet événement marquera le lancement officiel de la Maison du Quantique en Occitanie dont l'Université de Montpellier est partenaire au travers de l'ISDM. Cette journée sera un moment privilégié pour renforcer les collaborations, échanger sur les projets en cours et explorer de nouvelles opportunités dans le domaine.

Campus Triolet - Amphithéâtre Bat. 20 ISDM Rejoignez-nous le 30 avril à partir de 15h sur le campus Triolet de l’Université de Montpellier pour célébrer la mise en service du nouveau équipement de calcul/cloud ISDM-MESO / Drocc-Est ! Grâce au financement obtenu dans le cadre du CPER par l’Etat, la Région Occitanie, la Métropole de Montpellier et l’Université de Montpellier, l'ISDM renouvelle ses infrastructures de calcul et vous invite à découvrir cette nouvelle configuration de pointe et les services associés. Un cocktail suivra la présentation. Inscription gratuite mais obligatoire - présence possible à distance.

Salle 104 du bâtiment 11 dit le château, 2 Place Pierre Viala Campus La Gaillarde Le séminaire commencera par un café offert par les Halles de l'IA. Au programme : (1) News du W3C en 10 minutes, par Pierre-Antoine CHAMPIN, W3C / INRIA / Université de Lyon (2) Propagation de propriétés entre entités contextuellement identiques par Pierre Henri PARIS, Universite Paris-Saclay :

Online Machine Learning in Montpellier, Theory & Practice - Evan Munro (UC Berkeley) We consider the problem of learning how to optimally allocate treatments whose cost is uncertain and can vary with pre-treatment covariates. This setting may arise in medicine if we need to prioritize access to a scarce resource that different patients would use for different amounts of time, or in marketing if we want to target discounts whose cost to the company depends on how much the discounts are used. Here, we show that the optimal treatment allocation rule under budget constraints is a thresholding rule based on priority scores, and we propose a number of practical methods for learning these priority scores using data from a randomized trial. Our formal results leverage a statistical connection between our problem and that of learning heterogeneous treatment effects under endogeneity using an instrumental variable. We find our method to perform well in a number of empirical evaluations. Machine Learning in Montpellier, Theory & Practice

Campus Triolet, Pl. Eugène Bataillon, Bat 4, SC 4.04 Jonathan Dubois Venez découvrir un langage performant et ludique pour l'analyse statistique et la manipulation de données. Cette formation est une introduction à la programmation avec le langage R pour l’analyse statistique. #Formation, #Programmation, #Statistique, #R, #RStudio

Inria Montpellier, St-Priest Campus, Building 5, Room 02/022 Machine Learning in Montpellier, Theory & Practice In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of breakdown point, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule, coined CSours, such that CSours-RG has a near-optimal breakdown. Other choices of aggregation rules lead to existing algorithms such as ClippedGossip or NNA. We give experimental evidence to validate the effectiveness of CSours-RG and highlight the gap with NNA, in particular against a novel attack tailored to decentralized communications. MachineLearning, LabéliséHallesIA, IA&Expert

Room 02.249, Building 5, St Priest campus Machine Learning in Montpellier, Theory & Practice - Hadrien Hendrikx (Inria) In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of breakdown point, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule, coined CSours, such that CSours-RG has a near-optimal breakdown. Other choices of aggregation rules lead to existing algorithms such as ClippedGossip or NNA. We give experimental evidence to validate the effectiveness of CSours-RG and highlight the gap with NNA, in particular against a novel attack tailored to decentralized communications Machine Learning in Montpellier, Theory & Practice

Espace Richter - rue Vendémiaire - Montpellier (Salle B001 – Bât. B) Un workshop consacré à la digitalisation en management, financé par le Pôle sciences sociales de l'Université de Montpellier et le Laboratoire MRM. Nous aurons l’honneur d’accueillir pendant ces deux jours comme invité Wim Vanhaverbeke, rédacteur en chef de Technovation (FNEGE 2, ABS 3), reconnu internationalement pour ses travaux sur la transformation digitale et l’innovation ouverte. #Management, #LabéliséHallesIA

Online Machine Learning in Montpellier, Theory & Practice - Xinwei Shen (ETH Zürich) Distributional regression aims to estimate the full conditional distribution of a target variable, given covariates. Popular methods include linear and tree ensemble based quantile regression. We propose a neural networkbased distributional regression methodology called ‘engression’. An engression model is generative in the sense that we can sample from the fitted conditional distribution and is also suitable for high-dimensional outcomes. Furthermore, we find that modelling the conditional distribution on training data can constrain the fitted function outside of the training support, which offers a new perspective to the challenging extrapolation problem in nonlinear regression. In particular, for ‘preadditive noise’ models, where noise is added to the covariates before applying a nonlinear transformation, we show that engression can successfully perform extrapolation under some assumptions such as monotonicity, whereas traditional regression approaches such as least-squares or quantile regression fall short under the same assumptions. Our empirical results, from both simulated and real data, validate the effectiveness of the engression method. The software implementations of engression are available in both R and Python. Machine Learning in Montpellier, Theory & Practice

Montpellier Management FEET 3 jours pour échanger, questionner et inventer des solutions aux côtés de scientifiques et d’acteurs engagés #Forum, #Transition, #IA, #LabéliséHallesIA

Campus Triolet, Pl. Eugène Bataillon, Bat 4, SC 4.04 Jonathan Dubois Venez découvrir un langage performant et ludique pour l'analyse statistique et la manipulation de données. Cette formation est une introduction à la programmation avec le langage R pour l’analyse statistique. #Formation, #Programmation, #Statistique, #R, #RStudio

Hôtel de ville de Montpellier Incubateur du barreau de Montpellier - Village de la justice Découvrez les conférences, ateliers et débats sur deux jours pour explorer les innovations qui transforment la pratique du droit de demain. Journée, Droit

Castelnau-le-Lez Datasulting Une journée fun, sans bullshit ni langue de bois, avec de vrais "morceaux" d’expérience et de solutions dedans ! Vous êtes dirigeant ou décideur de PME et ETI en Occitanie et au delà ? Vous souhaitez exploiter et valoriser les données générées par votre activité ? Vous souhaitez savoir comment la gestion de ces données et/ou la mise en place de solutions d'IA pourraient booster votre performance ? Venez assister à la 4e édition de Cultive Ta Data [et ton IA] le 22 Mai 2025 au Domaine de Verchant ! #Journée, #LabéliséHallesIA

Polytech Montpellier Les étudiants de Polytech Conférence tech autour du Cloud et du DevOps organisée par des étudiants ! Polycloud est une journée de conférences gratuites qui tiendra sa quatrième édition le Samedi 24 mai 2025 à Polytech Montpellier. Le but est de faire découvrir le monde du cloud et du DevOps, au travers de conférences et d'activités pratiques. #Conférence, #PolytechMontpellier, #Cloud, #DevOps

Online Machine Learning in Montpellier, Theory & Practice - Pedro Valdeira (Carnegie Mellon) Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume that all feature partitions are available during both training and inference. Yet, in practice, this assumption rarely holds, as for many samples only a subset of the clients observe their partition. However, not utilizing incomplete samples during training harms generalization, and not supporting them during inference limits the utility of the model. Moreover, if any client leaves the federation after training, its partition becomes unavailable, rendering the learned model unusable. Missing feature blocks are therefore a key challenge limiting the applicability of vertical federated learning in real-world scenarios. To address this, we propose LASER VFL, a vertical federated learning method for efficient training and inference of split neural network-based models that is capable of handling arbitrary sets of partitions. Our approach is simple yet effective, relying on the sharing of model parameters and on task-sampling to train a family of predictors. We show that LASER-VFL achieves a convergence rate for nonconvex objectives and, under the Polyak-Łojasiewicz inequality, it achieves linear convergence to a neighborhood of the optimum. Numerical experiments show improved performance of LASER-VFL over the baselines. Remarkably, this is the case even in the absence of missing features. For example, for CIFAR-100, we see an improvement in accuracy of % when each of four feature blocks is observed with a probability of 0.5 and of % when all features are observed. The code for this work is available at https://isdm.umontpellier.fr/github.com/Valdeira/LASER-VFL. Machine Learning in Montpellier, Theory & Practice

Machine Learning in Montpellier, Theory & Practice - Pedro Valdeira Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume that all feature partitions are available during both training and inference. Yet, in practice, this assumption rarely holds, as for many samples only a subset of the clients observe their partition. However, not utilizing incomplete samples during training harms generalization, and not supporting them during inference limits the utility of the model. [...] Vertical Federated Learning, Missing Feature Blocks, LabéliséHallesIA