no code implementations • 2 Feb 2024 • Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman
Spherical harmonics are polynomials on the sphere that form an orthonormal basis of the set of square-integrable functions on the sphere.
no code implementations • 31 Oct 2023 • Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li, Aymeric Dieuleveut
Compression schemes have been extensively used in Federated Learning (FL) to reduce the communication cost of distributed learning.
no code implementations • 3 Aug 2023 • Rémi Leluc, Elie Kadoche, Antoine Bertoncello, Sébastien Gourvénec
Maintaining a balance between the supply and demand of products by optimizing replenishment decisions is one of the most important challenges in the supply chain industry.
no code implementations • 27 Jul 2022 • Hamid Jalalzai, Elie Kadoche, Rémi Leluc, Vincent Plassier
In this paper, we develop a mean to measure the leakage of training data leveraging a quantity appearing as a proxy of the total variation of a trained model near its training samples.
no code implementations • 24 May 2022 • Rémi Leluc, François Portier, Johan Segers, Aigerim Zhuman
Within the standard adaptive importance sampling framework, a simple weighted least squares approach is proposed to improve the procedure with control variates.
1 code implementation • 25 May 2021 • Rémi Leluc, François Portier
While classical forms of stochastic gradient descent algorithm treat the different coordinates in the same way, a framework allowing for adaptive (non uniform) coordinate sampling is developed to leverage structure in data.
no code implementations • 13 Aug 2020 • Hamid Jalalzai, Rémi Leluc
In the framework of multivariate Extreme Value Theory, a common characterization of extremes' dependence structure is the angular measure.
1 code implementation • 4 Jun 2020 • Rémi Leluc, François Portier
In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction.
no code implementations • 26 Jun 2019 • Rémi Leluc, François Portier, Johan Segers
Monte Carlo integration with variance reduction by means of control variates can be implemented by the ordinary least squares estimator for the intercept in a multiple linear regression model with the integrand as response and the control variates as covariates.
Statistics Theory Statistics Theory