no code implementations • 17 Oct 2023 • Antoine Salmona, Julie Delon, Agnès Desolneux
Our first contribution is the Mixture Gromov Wasserstein distance (MGW), which can be viewed as a Gromovized version of MW.
1 code implementation • 29 Jun 2022 • Antoine Salmona, Valentin De Bortoli, Julie Delon, Agnès Desolneux
More precisely, we show that the total variation distance and the Kullback-Leibler divergence between the generated and the data distribution are bounded from below by a constant depending on the mode separation and the Lipschitz constant.
no code implementations • 25 Oct 2021 • Valentin De Bortoli, Agnès Desolneux
Classical results require the invertibility of the Hessian of $U$ in order to establish such asymptotics.
no code implementations • 30 Jul 2020 • Darshan Venkatrayappa, Agnès Desolneux, Jean-Michel Hubert, Josselin Manceau
Later, we extract the residual image, which is the difference between the original image and the denoised (self-similar) image.
no code implementations • 23 Feb 2018 • Claire Launay, Bruno Galerne, Agnès Desolneux
The exact algorithm to sample DPPs uses the spectral decomposition of $K$, a computation that becomes costly when dealing with a high number of points.
no code implementations • 22 Jul 2017 • Lara Raad, Axel Davy, Agnès Desolneux, Jean-Michel Morel
The two main approaches are statistics-based methods and patch re-arrangement methods.