1 code implementation • 16 Feb 2024 • Hugo Lebeau, Mohamed El Amine Seddik, José Henrique de Morais Goulart
We study the estimation of a planted signal hidden in a recently introduced nested matrix-tensor model, which is an extension of the classical spiked rank-one tensor model, motivated by multi-view clustering.
no code implementations • 28 Oct 2023 • Mohamed El Amine Seddik, Maxime Guillaud, Alexis Decurninge, José Henrique de Morais Goulart
This work introduces an asymptotic study of Hotelling-type tensor deflation in the presence of noise, in the regime of large tensor dimensions.
no code implementations • 20 Apr 2023 • Mohamed El Amine Seddik, José Henrique de Morais Goulart, Maxime Guillaud
This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian noise.
no code implementations • 13 Jul 2022 • Arthur Marmin, José Henrique de Morais Goulart, Cédric Févotte
It is well known that the norm of the other factor (the dictionary matrix) needs to be controlled in order to avoid an ill-posed formulation.
no code implementations • 2 Aug 2021 • José Henrique de Morais Goulart, Romain Couillet, Pierre Comon
A numerical verification provides evidence that the same holds for orders 4 and 5, leading us to conjecture that, for any order, our fixed-point equation is equivalent to the known characterization of the ML estimation performance that had been obtained by relying on spin glasses.
no code implementations • 12 Jul 2021 • Phillip M. S. Burt, José Henrique de Morais Goulart
As previously shown, the direct extension of the impulse invariance principle to Volterra kernels has to be modified in order to provide a condition for the exact modeling of mixed-signal chains.
no code implementations • 29 Jun 2021 • Arthur Marmin, José Henrique de Morais Goulart, Cédric Févotte
Our new updates are derived from a joint majorization-minimization (MM) scheme, in which an auxiliary function (a tight upper bound of the objective function) is built for the two factors jointly and minimized at each iteration.