Publications

Amaury Bélières--Frendo, Emmanuel Franck, Victor Michel-Dansac, Yannick Privat. Volume-Preserving Geometric Shape Optimization of the Dirichlet Energy Using Variational Neural Networks. Neural Networks, 2025, 184, pp.106957. ⟨10.1016/j.neunet.2024.106957⟩. ⟨hal-04663197v3⟩
Erell Gachon, Jérémie Bigot, Elsa Cazelles, Audrey Bidet, Jean-Philippe Vial, et al.. Low dimensional representation of multi-patient flow cytometry datasets using optimal transport for minimal residual disease detection in leukemia. Cytometry Part A, 2025. ⟨hal-04661639⟩
Théo Matricon, Nathanaël Fijalkow, Guillaume Lagarde. EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis. Proceedings (AAAI Artificial Intelligence and Interactive Digital Entertainment Conference), In press, ⟨10.48550/arXiv.2412.17330⟩. ⟨hal-04901266⟩
Marina Costantini, Nikolaos Liakopoulos, Panayotis Mertikopoulos, Thrasyvoulos Spyropoulos. Setwise Coordinate Descent for Dual Asynchronous Decentralized Optimization. IEEE Transactions on Automatic Control, In press, pp.1-16. ⟨10.1109/TAC.2025.3543463⟩. ⟨hal-04991641⟩
Joubine Aghili, Romain Hild, Victor Michel-Dansac, Vincent Vigon, Emmanuel Franck. Accelerating the convergence of Newton's method for nonlinear elliptic PDEs using Fourier neural operators. Communications in Nonlinear Science and Numerical Simulation, 2025, 140 (2), pp.108434. ⟨10.1016/j.cnsns.2024.108434⟩. ⟨hal-04440076v4⟩
Bastien Doignies, David Coeurjolly, Nicolas Bonneel, Julie Digne, Jean-Claude Iehl, et al.. Differentiable Owen Scrambling. ACM Transactions on Graphics, 2024, proceeding of Siggraph ASIA 2024, 43 (6), pp.255. ⟨10.1145/3687764⟩. ⟨hal-04721127⟩
Eloi Tanguy, Rémi Flamary, Julie Delon. Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance. Comptes Rendus. Mathématique, 2024, 362, pp.1121--1129. ⟨hal-04232769v2⟩
Akwum Onwunta, Clément Royer. Complexity Analysis of Regularization Methods for Implicitly Constrained Least Squares. Journal of Scientific Computing, 2024, 101 (3), pp.54. ⟨10.1007/s10915-024-02691-2⟩. ⟨hal-04745284⟩
Prachi Kashikar, Olivier Sentieys, Sharad Sinha. Combining Weight Approximation, Sharing and Retraining for Neural Network Model Compression. ACM Transactions on Embedded Computing Systems (TECS), 2024, 23, pp.1 - 23. ⟨10.1145/3687466⟩. ⟨hal-04764621⟩
Antonin Chambolle, Michał Łasica. Inclusion and estimates for the jumps of minimizers in variational denoising. SIAM Journal on Imaging Sciences, 2024, 17 (3), pp.1844-1878. ⟨10.1137/23M1627948⟩. ⟨hal-04323807v2⟩
Panayotis Mertikopoulos, William H Sandholm. Nested replicator dynamics, nested logit choice, and similarity-based learning. Journal of Economic Theory, 2024, 220, pp.105881. ⟨10.1016/j.jet.2024.105881⟩. ⟨hal-04733800⟩
Panayotis Mertikopoulos, Heinrich H Nax, Bary S R Pradelski. Quick or cheap? Breaking points in dynamic markets. Journal of Mathematical Economics, 2024, 112, pp.102987. ⟨10.1016/j.jmateco.2024.102987⟩. ⟨hal-04664218⟩
Hamza Ennaji, Quentin Mérigot, Luca Nenna, Brendan Pass. Robust risk management via multi-marginal optimal transport. Journal of Optimization Theory and Applications, 2024, 202 (2), pp.554-581. ⟨10.1007/s10957-024-02438-x⟩. ⟨hal-03852245⟩
Elise Crépon, Aurélien Garivier, Wouter M Koolen. Sequential Learning of the Pareto Front for Multi-objective Bandits. Proceedings of Machine Learning Research, 2024, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR (238), pp.3583--3591. ⟨hal-04916328⟩
Antoine Picard-Weibel, Gabriel Capson-Tojo, Benjamin Guedj, Roman Moscoviz. Bayesian Uncertainty Quantification for Anaerobic Digestion models. Bioresource Technology, 2024, 394, ⟨10.1016/j.biortech.2023.130147⟩. ⟨hal-04592670⟩
Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen. THE LIPSCHITZ-VARIANCE-MARGIN TRADEOFF FOR ENHANCED RANDOMIZED SMOOTHING. ICLR International Conference on Learning Representations, 2024, The Twelfth International Conference on Learning Representations. ⟨hal-04867277⟩
Marco Campion, Mila Dalla Preda, Roberto Giacobazzi, Caterina Urban. Monotonicity and the Precision of Program Analysis. Proceedings of the ACM on Programming Languages, 2024, 8 (POPL), pp.1629-1662. ⟨10.1145/3632897⟩. ⟨hal-04423578⟩
Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard. Bandits with Stochastic Corruption: Lower Bounds on Regret and Robust Optimistic Algorithms. Transactions on Machine Learning Research Journal, 2024. ⟨hal-04615733v2⟩
Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. The rate of convergence of Bregman proximal methods: Local geometry vs. regularity vs. sharpness. SIAM Journal on Optimization, 2024, 34 (3), pp.2440-2471. ⟨10.1137/23M1580218⟩. ⟨hal-04307796⟩
Eloi Tanguy, Rémi Flamary, Julie Delon. Properties of Discrete Sliced Wasserstein Losses. Mathematics of Computation, 2023, ⟨https://doi.org/10.1090/mcom/3994⟩. ⟨hal-04232766v3⟩

Communications dans un congrès75 document

Majid Arthaud, Antonin Chambolle, Vincent Duval. A variational method for curve extraction. SSVM 2025 - 10th Scale-Space and Variational Methods in Computer Vision, May 2025, Totnes, Devon, United Kingdom. ⟨hal-04980911⟩
Romain Bouarah, Florent de Dinechin. Hardware Fixed-Point 2D and 3D norms. 32nd IEEE International Symposium on Computer Arithmetic - ARITH 2025, May 2025, El Paso, Texas, United States. ⟨hal-04986776⟩
Rémi Garcia, Léo Pradels, Silviu-Ioan Filip, Olivier Sentieys. Hardware-Aware Training for Multiplierless Convolutional Neural Networks. ARITH 2025 - 32nd IEEE International Symposium on Computer Arithmetic, May 2025, El Paso, United States. pp.1-8. ⟨hal-04949886v2⟩
Orégane Desrentes, Benoît Dupont de Dinechin, Florent de Dinechin. Double-Word Decomposition in a Combined FP16, BF16 and FP32 Dot Product Add Operator. ARITH 2025 - IEEE 32nd International Symposium on Computer Arithmetic, May 2025, El-Paso, Texas, United States. ⟨hal-04982397v2⟩
Julien Hermant, Marien Renaud, Jean-François Aujol, Charles Dossal, Aude Rondepierre. Gradient correlation is a key factor to accelerate SGD with momentum. International Conference on Learning Representations, 2025, Apr 2025, Singapour, Singapore. ⟨hal-04728121v2⟩
Sami Ben Ali, Silviu-Ioan Filip, Olivier Sentieys, Guy Lemieux. MPTorch-FPGA: a Custom Mixed-Precision Framework for FPGA-based DNN Training. DATE 2025 - 28th IEEE/ACM Design, Automation and Test in Europe, Mar 2025, Lyon, France. pp.1-6. ⟨hal-04882989v2⟩
Jonathan Geuter, Clément Bonet, Anna Korba, David Alvarez-Melis. DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows. International Conference on Artificial Intelligence and Statistics (AISTATS), Mar 2025, Mai Khao, France. ⟨hal-04989008⟩
Constantin Philippenko, Kevin Scaman, Laurent Massoulié. In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting. AAAI 2025 - 39th Annual AAAI Conference on Artificial Intelligence, Feb 2025, Philadelphia, United States. ⟨hal-04893622⟩
Maxime Haddouche, Paul Viallard, Umut Şimşekli, Benjamin Guedj. A PAC-Bayesian Link Between Generalisation and Flat Minima. ALT 2025 - 36th International Conference on Algorithmic Learning Theory, Feb 2025, Milan, Italy. pp.1-31. ⟨hal-04455639v2⟩
Feodor F. Dragan, Guillaume Ducoffe, Michel Habib, Laurent Viennot. Certificates in P and Subquadratic-Time Computation of Radius, Diameter, and all Eccentricities in Graphs. Proceedings of the 2025 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), Jan 2025, New Orleans (LA), United States. pp.2157--2193, ⟨10.1137/1.9781611978322.70⟩. ⟨hal-01729748v4⟩
Mathieu Molina, Nicolas Gast, Patrick Loiseau, Vianney Perchet. Prophet Inequalities: Competing with the Top $\ell$ Items is Easy. SODA 2025 - ACM-SIAM Symposium on Discrete Algorithms, Jan 2025, New Orleans, United States. pp.1-45. ⟨hal-04912640⟩
Fajwel Fogel, Yohann Perron, Nikola Besic, Laurent Saint-André, Agnès Pellissier-Tanon, et al.. Open-Canopy: Towards Very High Resolution Forest Monitoring. CVPR, 2025, Nashville (Tenessee), United States. ⟨hal-04710775⟩
Ziyad Benomar, Evgenii Chzhen, Nicolas Schreuder, Vianney Perchet. Addressing Bias in Online Selection with Limited Budget of Comparisons. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (CA), Canada. ⟨hal-04854073⟩
Yannis Karmim, Marc Lafon, Raphaël Fournier-S'Niehotta, Nicolas Thome. Supra-Laplacian Encoding for Transformer on Dynamic Graphs. The Thirty-eighth Annual Conference on Neural Information Processing Systems, Dec 2024, Vancouver (CA), Canada. ⟨hal-04785441⟩
Kyriakos Lotidis, Angeliki Giannou, Panayotis Mertikopoulos, Nicholas Bambos. Accelerated regularized learning in finite N-person games. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. pp.1-30. ⟨hal-04863626⟩
Matilde Tullii, Solenne Gaucher, Nadav Merlis, Vianney Perchet. Improved Algorithms for Contextual Dynamic Pricing. NeurIPS 2024 - The 38th Annual Conference on Neural Information Processing Systems, Dec 2024, Vancouver (BC), Canada. ⟨hal-04887635⟩
Nadav Merlis, Dorian Baudry, Vianney Perchet. The Value of Reward Lookahead in Reinforcement Learning. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. ⟨hal-04893988⟩
Dorian Baudry, Hugo Richard, Maria Cherifa, Clément Calauzènes, Vianney Perchet. Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (BC), Canada. ⟨hal-04896482⟩
Adrienne Tuynman, Rémy Degenne, Emilie Kaufmann. Finding good policies in average-reward Markov Decision Processes without prior knowledge. NeurIPS, Dec 2024, Vancouver (Canada), Canada. ⟨hal-04809429⟩
Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli. Optimal Multi-Fidelity Best-Arm Identification. Advances in Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver (BC), Canada. ⟨hal-04811199⟩
Ziyad Benomar, Dorian Baudry, Vianney Perchet. Lookback Prophet Inequalities. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (CA), Canada. ⟨hal-04854065⟩
Marius Potfer, Dorian Baudry, Hugo Richard, Vianney Perchet, Cheng Wang. Improved learning rates in multi-unit uniform price auctions. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (BC), Canada. ⟨hal-04896481⟩
Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba. Mirror and Preconditioned Gradient Descent in Wasserstein Space. Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver, Canada. ⟨hal-04703424⟩
Clémentine Chazal, Anna Korba, Francis Bach. Statistical and Geometrical Properties of Regularized Kernel Kullback-Leibler Divergence. Neurips 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. ⟨hal-04895033⟩
Davide Legacci, Panayotis Mertikopoulos, Christos Papadimitriou, Georgios Piliouras, Bary S R Pradelski. No-regret learning in harmonic games: Extrapolation in the face of conflicting interests. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. pp.1-36. ⟨hal-04863624⟩
Alessio Spagnoletti, Alexandre Boucaud, Marc Huertas-Company, Wassim Kabalan, Biswajit Biswas. Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions. 38th conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. ⟨hal-04816601⟩
Antoine Picard-Weibel, Roman Moscoviz, Benjamin Guedj. Learning via Surrogate PAC-Bayes. NeurIPS 2024, Dec 2024, Vancouver, Canada. ⟨hal-04731841v2⟩
Ayoub Ajarra, Bishwamittra Ghosh, Debabrota Basu. Active Fourier Auditor for Estimating Distributional Properties of ML Models. NeurIPS 2024 Workshop on Regulatable ML, Dec 2024, Vancouver (BC), Canada. ⟨hal-04733059⟩
Apurv Shukla, Debabrota Basu. Preference-based Pure Exploration. Advances in Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver (CA), Canada. ⟨hal-04733134v2⟩
Reuben Adams, John Shawe-Taylor, Benjamin Guedj. Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound. NeurIPS 2024 - Annual Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. ⟨hal-03573458⟩
Hugo Boulissière, Adrien Prost-Boucle, Elena Ioana Vatajelu, Giorgio Di Natale. Autonomous FPGA Reconfigurability in Embedded Systems. 20th IEEE East-West Design & Test Symposium (EWDTS 2024), IEEE, Nov 2024, Yerevan, Armenia. ⟨hal-04917041⟩
Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen. Chain and Causal Attention for Efficient Entity Tracking. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Nov 2024, Miami, United States. ⟨hal-04731420⟩
Omar Adjali, Olivier Ferret, Sahar Ghannay, Hervé Le Borgne. Multi-Level Information Retrieval Augmented Generation for Knowledge-based Visual Question Answering. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024, Miami, United States. pp.16499-16513, ⟨10.18653/v1/2024.emnlp-main.922⟩. ⟨hal-04852275⟩
Zhuofan Xu, Benedikt Bollig, Matthias Függer, Thomas Nowak. Permutation Equivariant Deep Reinforcement Learning for Multi-Armed Bandit. 36th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Oct 2024, Herndon, United States. ⟨10.1109/ICTAI62512.2024.00140⟩. ⟨hal-04787072⟩
Denis Mazzucato, Marco Campion, Caterina Urban. Quantitative Static Timing Analysis. 31st Static Analysis Symposium (SAS 2024), Roberto Giacobazzi; Alessandra Gorla; Marco Campion, Oct 2024, Pasadena, CA, United States. ⟨hal-04669723⟩
Ben Batten, Yang Zheng, Alessandro De Palma, Panagiotis Kouvaros, Alessio Lomuscio. Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation. ECAI 2024 - European Conference on Artificial Intelligence, Oct 2024, Santiago de Compostela, Spain. ⟨hal-04727955⟩
Udvas Das, Debabrota Basu. Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints. Seventeenth European Workshop on Reinforcement Learning (EWRL), Oct 2024, Toulouse, France. ⟨hal-04784911⟩
Nicolo Bellarmino, Alberto Bosio, Riccardo Cantoro, Annachiara Ruospo, Ernesto Sanchez, et al.. Investigating on Gradient Regularization for Testing Neural Networks. LOD 2024 : 10th International Conference on machine Learning, Optimization and Data science, Sep 2024, Riva de Sole, Italy. ⟨hal-04604264⟩
Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Michele Sebag, Marc Schoenauer. Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges. IJCAI 2024 - Survey Track, Aug 2024, Jeju, South Korea. pp.8207-8215, ⟨10.24963/ijcai.2024/907⟩. ⟨hal-04706985⟩
Thomas Firmin, Pierre Boulet, El-Ghazali Talbi. Asynchronous Multi-fidelity Hyperparameter Optimization Of Spiking Neural Networks. International Conference on Neuromorphic Systems (ICONS 2024), Jul 2024, Washington, United States. ⟨hal-04781629⟩
Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. What is the long-run distribution of stochastic gradient descent? A large deviations analysis. ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. pp.1-70. ⟨hal-04629305⟩
Sibylle Marcotte, Rémi Gribonval, Gabriel Peyré. Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows. 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. ⟨hal-04590932⟩
Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Kevin Scaman, Giovanni Neglia. Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm. ICML 2024 - The Forty-first International Conference on Machine Learning, Jul 2024, Vienne, Austria. ⟨hal-04611418⟩
Romain Xu-Darme, Aymeric Varasse, Alban Grastien, Julien Girard, Zakaria Chihani. CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Models. xAI 2024 - The 2nd World Conference on eXplainable Artificial Intelligence, Jul 2024, La valette, Malta. pp.TBD. ⟨cea-04688217v2⟩
Davide Legacci, Panayotis Mertikopoulos, Bary Pradelski. A geometric decomposition of finite games: Convergence vs. recurrence under exponential weights. ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. ⟨hal-04629310⟩
Andreas Kontogiannis, Vasilis Pollatos, Sotiris Kanellopoulos, Panayotis Mertikopoulos, Aris Pagourtzis, et al.. The computational complexity of finding second-order stationary points. ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. ⟨hal-04629307⟩
Achraf Azize, Debabrota Basu. Open Problem: What is the Complexity of Joint Differential Privacy in Linear Contextual Bandits?. Proceedings of Thirty Seventh Conference on Learning Theory, Jul 2024, Edmonton (Alberta), Canada. ⟨hal-04621903⟩
Imane Taibi, Jan Ramon. Honest Fraction Differential Privacy. ACM workshop on information hiding and multimedia security, ACM, Jun 2024, Vigo, Spain. pp.1-5, ⟨10.1145/3658664.3659655⟩. ⟨hal-04610199⟩
Joseph Gergaud, Jean-Baptiste Caillau, Olivier Cots, Pierre Martinon. control-toolbox: solving control problems within Julia. FGS 2024 - 21st French-German-Spanish conferences on Optimization, Oviedo University, Jun 2024, Gijón, Asturias, Spain. à paraître. ⟨hal-04651475⟩
Lionel Eyraud-Dubois, Guillaume Iooss, Julien Langou, Fabrice Rastello. Tightening I/O Lower Bounds through the Hourglass Dependency Pattern. SPAA 2024 - 36th ACM Symposium on Parallelism in Algorithms and Architectures, Jun 2024, Nantes, France. pp.1-34. ⟨hal-04555744⟩
Denis Mazzucato, Marco Campion, Caterina Urban. Quantitative Input Usage Static Analysis. NASA Formal Methods 2024, Jun 2024, Moffett Field (CA), United States. pp.79-98, ⟨10.1007/978-3-031-60698-4_5⟩. ⟨hal-04339001v3⟩
Marcello Traiola, Salvatore Pappalardo, Ali Piri, Annachiara Ruospo, Bastien Deveautour, et al.. Approximate Fault-Tolerant Neural Network Systems. ETS 2024 - 29th IEEE European Test Symposium, May 2024, La Haye, Netherlands. pp.1-10, ⟨10.1109/ETS61313.2024.10567290⟩. ⟨hal-04674818⟩
Lise Le Boudec, Emmanuel de Bézenac, Louis Serrano, Yuan Yin, Patrick Gallinari. Learning iterative algorithms to solve PDEs. ICLR 2024 Workshop on AI4DifferentialEquations In Science, ICLR 2024 Workshop, May 2024, Vienne (Austria), France. https://ai4diffeqtnsinsci.github.io. ⟨hal-04821571⟩
Marien Renaud, Jiaming Liu, Valentin de Bortoli, Andrés Almansa, Ulugbek Kamilov. Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models. (ICLR 2024) The Twelfth International Conference on Learning Representations, May 2024, Wien, Austria. ⟨hal-04307874⟩
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M Pawan Kumar, Robert Stanforth, et al.. Expressive Losses for Verified Robustness via Convex Combinations. ICLR 2024 - International Conference on Learning Representations, May 2024, Vienna, Austria. ⟨hal-04511820⟩
Mehdi Zadem, Sergio Mover, Sergio Mover, Sao Mai Nguyen. Reconciling Spatial and Temporal Abstractions for Goal Representation. ICLR 2024: Twelfth International Conference on Learning Representations, May 2024, Vienna, Austria. ⟨hal-04629549⟩
Kevin Scaman, Mathieu Even, Batiste Le Bars, Laurent Massoulié. Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles. AISTATS 2024 - International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain. ⟨hal-04895743⟩
Cyrille Kone, Emilie Kaufmann, Laura Richert. Bandit Pareto Set Identification: the Fixed Budget Setting. AISTATS 2024 - 27th International Conference on Artifi- cial Intelligence and Statistics, May 2024, Valencia, Spain. ⟨hal-04877368⟩
Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li, Aymeric Dieuleveut. Compression with Exact Error Distribution for Federated Learning. International Conference on Artificial Intelligence and Statistics, May 2024, Valencia (Espagne), Spain. pp.613-621. ⟨hal-04554506⟩
Hannes Eriksson, Tommy Tram, Debabrota Basu, Mina Alibeigi, Christos Dimitrakakis. Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer. 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2024, Auckland, New Zealand. pp.516-524, ⟨10.5555/3635637.3662902⟩. ⟨hal-04260795⟩
Amélie Gruel, Adrien Vincent, Jean Martinet, Sylvain Saïghi. Neuromorphic Event-based Line Detection on SpiNNaker. 2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS), Apr 2024, Abu Dhabi, France. pp.36-40, ⟨10.1109/AICAS59952.2024.10595959⟩. ⟨hal-04886230⟩
Pierre Lewden, Adrien Vincent, Jean Tomas, Chip-Hong Chang, Sylvain Saïghi. Effect of Line Resistance of Passive Memristive Crossbars on Spiking Neural Network Performance. 2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS), Apr 2024, Abu Dhabi, France. pp.403-407, ⟨10.1109/AICAS59952.2024.10595965⟩. ⟨hal-04886340⟩
Achraf Azize, Debabrota Basu. Concentrated Differential Privacy for Bandits. 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), IEEE, Apr 2024, Toronto, Canada. pp.78-109, ⟨10.1109/SaTML59370.2024.00013⟩. ⟨hal-04611650⟩
Cristiana Bolchini, Alberto Bosio. Resilience of deep learning applications: where we are and where we want to go. 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), Mar 2024, Valencia (Espagne), Spain. ⟨hal-04674837⟩
Sami Ben Ali, Silviu-Ioan Filip, Olivier Sentieys. A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training. DATE 2024 - 27th IEEE/ACM Design, Automation and Test in Europe, Mar 2024, Valencia, Spain. pp.1-6. ⟨hal-04380270v3⟩
Florian Le Bronnec, Song Duong, Mathieu Ravaut, Alexandre Allauzen, Nancy F. Chen, et al.. LOCOST: State-Space Models for Long Document Abstractive Summarization. European Chapter of the Association for Computational Linguistics (EACL), Mar 2024, St. Julian’s, Malta. ⟨hal-04438465⟩
Shubhada Agrawal, Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard. CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption. International Conference on Algorithmic Learning Theory (ALT), Feb 2024, San Diego (CA), United States. pp.74-124. ⟨hal-04260464⟩
Abhinandan Pal, Francesco Ranzato, Caterina Urban, Marco Zanella. Abstract Interpretation-Based Feature Importance for Support Vector Machines. 25th International Conference on Verification, Model Checking, and Abstract Interpretation (VMCAI 2024), Jan 2024, London, United Kingdom. pp.27-49, ⟨10.1007/978-3-031-50524-9_2⟩. ⟨hal-04378817⟩
Romain Loiseau, Elliot Vincent, Mathieu Aubry, Loic Landrieu. Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans. CVPR, 2024, Seattle (USA), United States. ⟨hal-04135416⟩
Felipe Garrido-Lucero, Benjamin Heymann, Maxime Vono, Patrick Loiseau, Vianney Perchet. DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation. Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024, Vancouver, Canada. ⟨hal-04420286⟩
Cédric Gernigon, Silviu-Ioan Filip, Olivier Sentieys, Clément Coggiola, Mickael Bruno. AdaQAT: Adaptive Bit-Width Quantization-Aware Training. IEEE 6th International Conference on AI Circuits and Systems (AICAS), 2024, Abu Dhabi, United Arab Emirates. ⟨hal-04549245⟩
Antonin Joly, Nicolas Keriven. Graph Coarsening with Message-Passing Guarantees. Advances in Neural Information Processing Systems (NeurIPS), 2024, Vancouver, Canada. ⟨hal-04617519⟩
Léo Henry, Blaise Genest, Alexandre Drewery. Reinforcement Planning for effective ε-optimal policies in dense time with discontinuities. 43rd IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science, Dec 2023, hyderabad, India. ⟨10.4230/LIPIcs⟩. ⟨hal-04280462⟩
Achraf Azize, Marc Jourdan, Aymen Al Marjani, Debabrota Basu. On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence. NeurIPS 2023 – Conference on Neural Information Processing Systems, Dec 2023, New Orleans (US), United States. pp.71150--71194. ⟨hal-04215474⟩
Jean-Baptiste Caillau, Olivier Cots, Joseph Gergaud, Pierre Martinon. Solving optimal control problems with Julia. Julia and Optimization Days 2023, CNAM; CNRS - Groupe CALCUL, Oct 2023, Paris, France. ⟨hal-04277441⟩

Proceedings/Recueil des communications1 document

Eric Goubault, Sylvie Putot. A Zonotopic Dempster-Shafer Approach to the Quantitative Verification of Neural Networks. International Symposium on Formal Methods, FM 2024, 14933, Springer Nature Switzerland, pp.324-342, 2025, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-71162-6_17⟩. ⟨hal-04546350v2⟩

Ouvrages (y compris édition critique et traduction)1 document

Florent de Dinechin, Martin Kumm. Application-Specific Arithmetic. Springer International Publishing, 2024, 978-3-031-42808-1. ⟨10.1007/978-3-031-42808-1⟩. ⟨hal-04715553⟩

Chapitres d'ouvrage1 document

Ana Pinzari, Adrien Prost-Boucle, Christelle Rabache, Frédéric Pétrot. Inside the AI Accelerators: From High Performance to Energy Efficiency. Ovidiu VERMESAN - Dave MARPLES. Advancing Edge Artificial Intelligence, River Publishers, pp.87-103, 2024, 9781003478713. ⟨10.1201/9781003478713-4⟩. ⟨hal-04465853⟩

Pré-publications, Documents de travail53 document

El-Mehdi El Arar, Silviu-Ioan Filip, Théo Mary, Elisa Riccietti. Mixed precision accumulation for neural network inference guided by componentwise forward error analysis. 2025. ⟨hal-04995708⟩
Alessio Spagnoletti, Jean Prost, Andrés Almansa, Nicolas Papadakis, Marcelo Pereyra. LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization. 2025. ⟨hal-04997921⟩
Jean-Jacques Godeme. Differentiation of inertial methods for optimizing smooth parametric function. 2025. ⟨hal-04907837v3⟩
Antoine Picard-Weibel, Eugenio Clerico, Roman Moscoviz, Benjamin Guedj. How good is PAC-Bayes at explaining generalisation?. 2025. ⟨hal-04989460⟩
El-Mehdi El Arar, Massimiliano Fasi, Silviu-Ioan Filip, Mantas Mikaitis. Probabilistic error analysis of limited-precision stochastic rounding. 2025. ⟨hal-04665809v3⟩
Rémi Gribonval, Elisa Riccietti, Quoc-Tung Le, Léon Zheng. Rapture of the deep: highs and lows of sparsity in a world of depths. 2025. ⟨hal-04954574⟩
Mélissa Tamine, Benjamin Heymann, Patrick Loiseau, Maxime Vono. On the Impact of the Utility in Semivalue-based Data Valuation. 2025. ⟨hal-04946103⟩
Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels, Samuel Vaiter. Bilevel gradient methods and Morse parametric qualification. 2025. ⟨hal-04942322⟩
Erell Gachon, Jérémie Bigot, Elsa Cazelles. Scalable and consistent embedding of probability measures into Hilbert spaces via measure quantization. 2025. ⟨hal-04941078⟩
Denis Sokolov. College Admissions in France: Affirmative Action, Overlapping Reserves, and Housing Quotas. 2025. ⟨hal-04896232v2⟩
Christophe Vauthier, Quentin Merigot, Anna Korba. Properties of Wasserstein Gradient Flows for the Sliced-Wasserstein Distance. 2025. ⟨hal-04963968⟩
Alexandre Marthe, Samuel Bounan, Aurélien Garivier, Claire Vernade. Efficient Risk-sensitive Planning via Entropic Risk Measures. 2025. ⟨hal-04967311⟩
Alexandre Fournier-Montgieux, Michael Soumm, Adrian Popescu, Bertrand Luvison, Hervé Le Borgne. Fairer analysis and demographically balanced face generation for fairer face verification. 2025. ⟨cea-04910990⟩
Julien Hermant, Jean-François Aujol, Charles Dossal, Aude Rondepierre. Study of the behaviour of Nesterov Accelerated Gradient in a non convex setting: the strongly quasar convex case. 2025. ⟨hal-04589853v2⟩
Antonin Chambolle, Jean-Michel Morel. Image = Cartoon+Texture: How Yves Meyer's "Oscillating patterns in image processing and in some nonlinear evolution equations" ended up in a computer vision model. 2025. ⟨hal-04893423⟩
Brandon A Mosqueda González, Omar Hasan, Lionel Brunie. Mitigation of Sybil-based Poisoning Attacks in Permissionless Decentralized Learning. 2025. ⟨hal-04892539⟩
Yann Traonmilin, Jean François Aujol, Antoine Guennec. Towards optimal algorithms for the recovery of low-dimensional models with linear rates. 2025. ⟨hal-04725337v2⟩
Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval. A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations. 2025. ⟨hal-04584311v3⟩
Paul Mangold, Alain Durmus, Aymeric Dieuleveut, Sergey Samsonov, Eric Moulines. Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation. 2025. ⟨hal-04878343⟩
Anne Gagneux, Mathurin Massias, Emmanuel Soubies, Rémi Gribonval. Convexity in ReLU Neural Networks: beyond ICNNs?. 2025. ⟨hal-04877619⟩
Benedikt Bollig, Matthias Függer, Thomas Nowak. A Framework for Streaming Event-Log Prediction in Business Processes. 2025. ⟨hal-04866045⟩
Cyril Letrouit, Quentin Mérigot. Gluing methods for quantitative stability of optimal transport maps. 2025. ⟨hal-04864913⟩
Eloi Tanguy, Julie Delon, Nathaël Gozlan. Computing Barycentres of Measures for Generic Transport Costs. 2024. ⟨hal-04852578⟩
Élie Bretin, Antonin Chambolle, Simon Masnou. A Cahn--Hilliard--Willmore phase field model for non-oriented interfaces. 2024. ⟨hal-04884780⟩
Lucas de Lara. A clarification on the links between potential outcomes and do-interventions. 2024. ⟨hal-04203003v4⟩
Marien Renaud, Julien Hermant, Nicolas Papadakis. Convergence Analysis of a Proximal Stochastic Denoising Regularization Algorithm. 2024. ⟨hal-04833501⟩
Antoine Guennec, Jean-François Aujol, Yann Traonmilin. Joint structure-texture low dimensional modeling for image decomposition with a plug and play framework. 2024. ⟨hal-04648963v3⟩
Pablo de Oliveira Castro, El-Mehdi El Arar, Eric Petit, Devan Sohier. Error Analysis of Sum-Product Algorithms under Stochastic Rounding. 2024. ⟨hal-04787542v2⟩
Tom Hubrecht, Orégane Desrentes, Florent de Dinechin. Activations in Low Precision with High Accuracy. 2024. ⟨hal-04776745⟩
Antoine Gonon, Léon Zheng, Pascal Carrivain, Quoc-Tung Le. Fast inference with Kronecker-sparse matrices. 2024. ⟨hal-04584450v4⟩
Chao Han, Debabrota Basu, Michael Mangan, Eleni Vasilaki, Aditya Gilra. Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs. 2024. ⟨hal-04785076⟩
Omar Adjali, Olivier Ferret, Sahar Ghannay, Hervé Le Borgne. Entity-aware cross-modal pretraining for Knowledge-Based Visual Question Answering. 2024. ⟨cea-04910767⟩
Charles Dossal, Samuel Hurault, Nicolas Papadakis. Optimization with First Order Algorithms. 2024. ⟨hal-04755998⟩
Debabrota Basu, Sourav Chakraborty, Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, et al.. Testing Credibility of Public and Private Surveys through the Lens of Regression. 2024. ⟨hal-04733076⟩
Naheed Anjum Arafat, Debabrota Basu, Yulia Gel, Yuzhou Chen. When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning. 2024. ⟨hal-04708183⟩
Aurélien Garivier, Emmanuel Pilliat. On Sparsity and Sub-Gaussianity in the Johnson-Lindenstrauss Lemma. 2024. ⟨hal-04690731v2⟩
Reabetswe M. Nkhumise, Debabrota Basu, Tony J. Prescott, Aditya Gilra. Measuring Exploration in Reinforcement Learning via Optimal Transport in Policy Space. 2024. ⟨hal-04702986⟩
Marius Belly, Nathanaël Fijalkow, Hugo Gimbert, Florian Horn, Guillermo Alberto Pérez, et al.. Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives. 2024. ⟨hal-04797702v3⟩
Eloi Tanguy, Agnès Desolneux, Julie Delon. Constrained Approximate Optimal Transport Maps. 2024. ⟨hal-04705433v2⟩
Sunrit Chakraborty, Saptarshi Roy, Debabrota Basu. FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits. 2024. ⟨hal-04615697⟩
Achraf Azize, Marc Jourdan, Aymen Al Marjani, Debabrota Basu. Differentially Private Best-Arm Identification. 2024. ⟨hal-04615690⟩
Léo Portales, Elsa Cazelles, Edouard Pauwels. On the sequential convergence of Lloyd's algorithms. 2024. ⟨hal-04593982v3⟩
Antonin Chambolle, Daniele de Gennaro, Massimiliano Morini. Discrete-to-continuous crystalline curvature flows. 2024. ⟨hal-04500307v2⟩
Eloi Tanguy. Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses. 2024. ⟨hal-04232792v2⟩
Jean-François Aujol, Charles Dossal, Hippolyte Labarrière, Aude Rondepierre. Heavy Ball Momentum for Non-Strongly Convex Optimization. 2024. ⟨hal-04500652⟩
Paul Viallard, Maxime Haddouche, Umut Şimşekli, Benjamin Guedj. Tighter Generalisation Bounds via Interpolation. 2024. ⟨hal-04456925⟩
Vitalii Emelianov, Michaël Perrot. On the Impact of Output Perturbation on Fairness in Binary Linear Classification. 2024. ⟨hal-04440982⟩
Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman. Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates. 2024. ⟨hal-04438124⟩
Fryderyk Falniowski, Panayotis Mertikopoulos. On the discrete-time origins of the replicator dynamics: From convergence to instability and chaos. 2024. ⟨hal-04629311⟩
Guillaume Iooss, Christophe Guillon, Fabrice Rastello, Albert Cohen, Saday Sadayappan. SARCASM: Set-Associative Rotating Cache Analytical/Simulating Model. 2024. ⟨hal-04814088⟩
Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx. Unified Breakdown Analysis for Byzantine Robust Gossip. 2024. ⟨hal-04830823v2⟩
Iosif Lytras, Panayotis Mertikopoulos. Tamed Langevin sampling under weaker conditions. 2024. ⟨hal-04629313⟩
Quoc-Tung Le, Léon Zheng, Elisa Riccietti, Rémi Gribonval. Butterfly factorization with error guarantees. 2024. ⟨hal-04763712⟩

Rapports2 document

Alban Dutilleul, Hugo Pompougnac, Nicolas Derumigny, Gabriel Rodríguez, Valentin Trophime, et al.. Performance debugging through microarchitectural sensitivity and causality analysis. INRIA. 2024, pp.1-13. ⟨hal-04851704⟩
Maxime Amisse, Mélissa Faur, Lucie Gonard, André Orcesi. Promouvoir des modèles d’intelligence artificielle frugale pour et par les politiques publiques. Ecole des Ponts Paris Tech, Paris-France. 2024. ⟨hal-04510171⟩

Thèses1 document

Denis Mazzucato. Static Analysis by Abstract Interpretation of Quantitative Program Properties. Computer Science [cs]. École Normale Supérieure, 2024. English. ⟨NNT : ⟩. ⟨tel-04886659⟩