863 citations
- J. Lasserre32 · h 51
- D. Henrion29 · h 45
- Victor Magron23 · h 20
- P. Wiecha20 · h 21
- R. Terrier2 profiles19 · h 68
- D. Horns2 profiles18 · h 69
- G. Henri2 profiles18 · h 57
- G. Hermann2 profiles18 · h 60
- M. Punch2 profiles18 · h 61
- F. Feinstein2 profiles17 · h 52
- J. Ripken2 profiles17 · h 59
- K. Kosack2 profiles17 · h 57
- Centre National de la Recherche ScientifiqueFR339 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR135 papers
- Université Toulouse III - Paul SabatierFR128 papers
- Université de ToulouseFR93 papers
- Institut National des Sciences Appliquées de ToulouseFR41 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR39 papers
- Czech Technical University in PragueCZ33 papers
- Institut de Mathématiques de ToulouseFR27 papers
- Sorbonne UniversitéFR27 papers
- CEA Paris-SaclayFR26 papers
- Université Grenoble AlpesFR23 papers
- École PolytechniqueFR22 papers
19 papers · 1 filter
Cost Trade-offs in Matrix Inversion Updates for Streaming Outlier Detection
Florian Grivet, Louise Travé-Massuyès
Outlier detection identifies data points that deviate significantly from expected patterns, revealing anomalies that may require special attention. Incorporating online learning fu…
Log Probability Tracking of LLM APIs
Timothée Chauvin, Erwan Le Merrer, François Taïani +1
When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the r…
Leveraging the Christoffel Function for Outlier Detection in Data Streams
Kévin Ducharlet, Louise Travé-Massuyès, Jean-Bernard Lasserre +2
Outlier detection holds significant importance in the realm of data mining, particularly with the growing pervasiveness of data acquisition methods. The ability to identify outlier…
Federated Majorize-Minimization: Beyond Parameter Aggregation
Aymeric Dieuleveut, Gersende Fort, Mahmoud Hegazy +1
This paper proposes a unified approach for designing stochastic optimization algorithms that robustly scale to the federated learning setting. Our work studies a class of Majorize-…
Robust ML Auditing using Prior Knowledge
Jade Garcia Bourrée, Augustin Godinot, Martijn De Vos +5
Among the many technical challenges to enforcing AI regulations, one crucial yet underexplored problem is the risk of audit manipulation. This manipulation occurs when a platform d…
The regret lower bound for communicating Markov Decision Processes
Victor Boone, Odalric-Ambrym Maillard
This paper is devoted to the extension of the regret lower bound beyond ergodic Markov decision processes (MDPs) in the problem dependent setting. While the regret lower bound for…