13 citations
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR7 papers
- Université de LilleFR7 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- École Centrale de LilleFR2 papers
- Laboratoire de Physique des PlasmasFR2 papers
- Laboratoire Paul PainlevéFR2 papers
- Centre Inria de l'Université de LilleFR1 paper
- École Normale Supérieure de LyonFR1 paper
- Google DeepMind (United Kingdom)GB1 paper
- Heriot-Watt UniversityGB1 paper
- Heriot-Watt University MalaysiaMY1 paper
- King's College LondonGB1 paper
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Quenched large deviations for Monte Carlo integration with Coulomb gases
Martin Rouault, Rémi Bardenet, Mylène Maïda
Gibbs measures, such as Coulomb gases, are popular in modelling systems of interacting particles. Recently, we proposed to use Gibbs measures as randomized numerical integration al…
cs.LG2026
Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding
Martin Rouault, Rémi Bardenet, Mylène Maïda
Kernel herding belongs to a family of deterministic quadratures that seek to minimize the maximum mean discrepancy (MMD), that is, the worst-case integration error over a reproduci…
cs.LG2026★ 13 cited
On two ways to use determinantal point processes for Monte Carlo integration
Guillaume Gautier, Rémi Bardenet, Michal Valko
The standard Monte Carlo estimator of relies on independent samples from and has variance of order . Replacing the samples with…