Jump to navigation
Marc Arnaudon, Koléhè Coulibaly-Pasquier, and Laurent Miclo
vol. 24, n. 183, 2024, pp. 1–43
Sébastien Gadat, and Clément Lalanne
vol. 235, “ICML'24: Proceedings of the 41st International Conference on Machine Learning”, 2024, pp. 25936 – 25975
Fueled by the ever-increasing need for statistics that guarantee the privacy of their training sets, this article studies the centrally-private estimation of Sobolev-smooth densities of probability over the hypercube in dimension d. The contributions of this article are two-fold : Firstly, it...
David Martimort, and Jérôme Pouyet
2024, forthcoming
Pay-TV firms compete both downstream to attract viewers and upstream to acquire broadcasting rights. Because profits inherited from downstream competition satisfy a Convexity Property, allocating rights to the dominant firm maximizes the industry profit. Such an exclusive allocation of rights...
Jean-Bernard Lasserre
2024
vol. 362, 2024, pp. 1455–1473
Jean-Bernard Lasserre, and Yuan Xu
Yukai Tang, Jean-Bernard Lasserre, and Heng Yang
2024, pp. 286–-298
Set-membership estimation (SME) outputs a set estimator that guarantees to cover the groundtruth. Such sets are, however, defined by (many) abstract (and potentially nonconvex) constraints and therefore difficult to manipulate. We present tractable algorithms to compute simple and tight...
Farid Gasmi, and Jose Aurazo
vol. 69, n. 101113, December 2024
Digitalization of retail payments has facilitated financial inclusion. This is recognized to stimulate growth, alleviate poverty, and address gender disparities in the financial sector. This paper closely examines four prominent payment solutions in the developing world, namely M-Pesa in Kenya, UPI...
Marelys Crespo, Sébastien Gadat, and Xavier Gendre
vol. 29, 2024, pp. 1–40
In this paper, we investigate a continuous time version of the Stochastic Langevin Monte Carlo method, introduced in [39], that incorporates a stochastic sampling step inside the traditional overdamped Langevin diffusion. This method is popular in machine learning for sampling posterior...
