336 citations
- J. Darmont2 profiles13 · h 23
- Julien Velcin4 profiles13 · h 13
- Genoveva Vargas-Solar6 · h 13
- Javier-Alfonso Espinosa-Oviedo6 · h 7
- Guillaume Metzler2 profiles4 · h 2
- Sabine Loudcher2 profiles4 · h 14
- A. Bouras3 · h 18
- A. Sekhari3 · h 13
- Gael Poux-Medard3 · h 6
- Irina Proskurina3 · h 4
- Jairo Cugliari2 profiles3 · h 9
- J. Jacques3 · h 19
- Entrepôts, Représentation et Ingénierie des ConnaissancesFR21 papers
- Lyon 1 UniversitéFR17 papers
- Centre National de la Recherche ScientifiqueFR11 papers
- Seattle Epidemiologic Information and Research CenterUS6 papers
- Laboratoire d'Informatique en Images et Systèmes d'InformationFR5 papers
- Aix-Marseille UniversitéFR3 papers
- Décision et Information pour les Systèmes de ProductionFR3 papers
- École Normale Supérieure de LyonFR3 papers
- Institut National des Sciences Appliquées de LyonFR3 papers
- Laboratoire Dynamique du LangageFR3 papers
- Qatar UniversityQA3 papers
- Chiang Mai UniversityTH2 papers
7 papers · 1 filter
PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun +3
We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This c…
Pr{é}diction optimale pour un mod{è}le ordinal {à} covariables fonctionnelles
Simón Weinberger, Jairo Cugliari, Aurélie Le Cain
We present a prediction framework for ordinal models: we introduce optimal predictions using loss functions and give the explicit form of the Least-Absolute-Deviation prediction fo…
Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall +2
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time ada…
Powered Dirichlet Process for Controlling the Importance of "Rich-Get-Richer" Prior Assumptions in Bayesian Clustering
Gaël Poux-Médard, Julien Velcin, Sabine Loudcher
One of the most used priors in Bayesian clustering is the Dirichlet prior. It can be expressed as a Chinese Restaurant Process. This process allows nonparametric estimation of the…
Information Interaction Profile of Choice Adoption
Gaël Poux-Médard, Julien Velcin, Sabine Loudcher
Interactions between pieces of information (entities) play a substantial role in the way an individual acts on them: adoption of a product, the spread of news, strategy choice, etc…
Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models
Alberto Lumbreras, Julien Velcin, Marie Guégan +1
We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density…