no code implementations • 13 Feb 2024 • Juan M. Miramont, Rémi Bardenet, Pierre Chainais, Francois Auger
For instance, detection and denoising based on the zeros of the spectrogram have been proposed since 2015, contrasting with a long history of focusing on larger values of the spectrogram.
no code implementations • 20 May 2023 • Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais
Normalizing flows (NF) use a continuous generator to map a simple latent (e. g. Gaussian) distribution, towards an empirical target distribution associated with a training data set.
1 code implementation • 21 Apr 2023 • Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais
This paper introduces a stochastic plug-and-play (PnP) sampling algorithm that leverages variable splitting to efficiently sample from a posterior distribution.
no code implementations • 12 Jul 2022 • Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais
Despite their advantages, normalizing flows generally suffer from several shortcomings including their tendency to generate unrealistic data (e. g., images) and their failing to detect out-of-distribution data.
1 code implementation • 4 Jul 2022 • Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais
Each of these functions is associated to one sub-flow of the network, whose output provides intermediate steps of the transport between the original and target measures.
1 code implementation • 4 Oct 2020 • Maxime Vono, Nicolas Dobigeon, Pierre Chainais
In addition to this state of the art, this paper proposes a unifying Gaussian simulation framework by deriving a stochastic counterpart of the celebrated proximal point algorithm in optimization.
Computation
no code implementations • 31 Aug 2020 • Pierre Gratier, Jérôme Pety, Emeric Bron, Antoine Roueff, Jan H. Orkisz, Maryvonne Gerin, Victor de Souza Magalhaes, Mathilde Gaudel, Maxime Vono, Sébastien Bardeau, Jocelyn Chanussot, Pierre Chainais, Javier R. Goicoechea, Viviana V. Guzmán, Annie Hughes, Jouni Kainulainen, David Languignon, Jacques Le Bourlot, Franck Le Petit, François Levrier, Harvey Liszt, Nicolas Peretto, Evelyne Roueff, Albrecht Sievers
We aim to use multi-molecule line emission to infer NH2 from radio observations.
Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
no code implementations • ICML 2020 • Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
A fundamental task in kernel methods is to pick nodes and weights, so as to approximate a given function from an RKHS by the weighted sum of kernel translates located at the nodes.
1 code implementation • NeurIPS 2019 • Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
We study quadrature rules for functions from an RKHS, using nodes sampled from a determinantal point process (DPP).
no code implementations • 15 Feb 2019 • Maxime Vono, Nicolas Dobigeon, Pierre Chainais
In a broader perspective, this paper shows that AXDA models can benefit from interesting statistical properties and yield efficient inference algorithms.
no code implementations • 23 Dec 2018 • Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
We give bounds on the ratio of the expected approximation error for this DPP over the optimal error of PCA.
1 code implementation • 7 Feb 2018 • Julien Flamant, Pierre Chainais, Nicolas Le Bihan
A complete framework for the linear time-invariant (LTI) filtering theory of bivariate signals is proposed based on a tailored quaternion Fourier transform.
no code implementations • 17 Sep 2017 • Clément Elvira, Pierre Chainais, Nicolas Dobigeon
The selection of the number of significant components is essential but often based on some practical heuristics depending on the application.
1 code implementation • 19 Mar 2017 • Julien Flamant, Nicolas Le Bihan, Pierre Chainais
This spectral density can be meaningfully interpreted in terms of frequency-dependent polarization attributes.
Methodology
1 code implementation • 8 Sep 2016 • Julien Flamant, Nicolas Le Bihan, Pierre Chainais
The resulting spectrograms and scalograms provide meaningful representations of both the time-frequency and geometrical/polarization content of the signal.
Methodology
no code implementations • 18 Dec 2015 • Clément Elvira, Pierre Chainais, Nicolas Dobigeon
Then this probability distribution is used as a prior to promote anti-sparsity in a Gaussian linear inverse problem, yielding a fully Bayesian formulation of anti-sparse coding.
no code implementations • 12 Apr 2013 • Pierre Chainais, Cédric Richard
We consider the problem of distributed dictionary learning, where a set of nodes is required to collectively learn a common dictionary from noisy measurements.