no code implementations • 30 Oct 2023 • Nathael Da Costa, Cyrus Mostajeran, Juan-Pablo Ortega, Salem Said
This work aims to prove that the classical Gaussian kernel, when defined on a non-Euclidean symmetric space, is never positive-definite for any choice of parameter.
no code implementations • 20 Oct 2023 • Nathael Da Costa, Cyrus Mostajeran, Juan-Pablo Ortega, Salem Said
Classical kernel methods are based on positive-definite kernels, which map data spaces into reproducing kernel Hilbert spaces (RKHS).
no code implementations • 2 Jul 2022 • Berlin Chen, Cyrus Mostajeran, Salem Said
We present a novel algorithm for learning the parameters of hidden Markov models (HMMs) in a geometric setting where the observations take values in Riemannian manifolds.
no code implementations • 1 Mar 2022 • Salem Said, Simon Heuveline, Cyrus Mostajeran
Its main contribution is to prove that Riemannian Gaussian distributions of real, complex, or quaternion covariance matrices are equivalent to orthogonal, unitary, or symplectic log-normal matrix ensembles.
no code implementations • 15 Feb 2021 • Alain Durmus, Pablo Jiménez, Éric Moulines, Salem Said
This result gives rise to a family of stationary distributions indexed by the step-size, which is further shown to converge to a Dirac measure, concentrated at the solution of the problem at hand, as the step-size goes to 0.
no code implementations • 15 Feb 2021 • Quinten Tupker, Salem Said, Cyrus Mostajeran
Hidden Markov models with observations in a Euclidean space play an important role in signal and image processing.
no code implementations • 26 Jan 2021 • Salem Said
This entry contains the core material of my habilitation thesis, soon to be officially submitted.
Statistics Theory Statistics Theory
no code implementations • 11 Jan 2021 • Salem Said, Nicolas Le Bihan, Jonathan H. Manton
Hidden Markov chain, or Markov field, models, with observations in a Euclidean space, play a major role across signal and image processing.
Statistics Theory Statistics Theory
no code implementations • 5 Nov 2020 • Jialun Zhou, Salem Said, Yannick Berthoumieu
To develop the ISG method, the Riemannian information gradient is derived taking into account the product manifold associated to the underlying parameter space of the ECD.
no code implementations • 27 May 2020 • Alain Durmus, Pablo Jiménez, Éric Moulines, Salem Said, Hoi-To Wai
This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems.
no code implementations • 20 May 2020 • Florent Bouchard, Ammar Mian, Jialun Zhou, Salem Said, Guillaume Ginolhac, Yannick Berthoumieu
A new Riemannian geometry for the Compound Gaussian distribution is proposed.