6 papers
Personalised federated learning for Riemannian and Euclidean EEG decoding
Thibault Pautrel, Florent Bouchard, Ammar Mian +1
Federated learning (FL) lets EEG decoders learn from recordings of several subjects without pooling them. We consider two light EEG decoders, the Riemannian SPDNet and the Euclidea…
Global universality of the expected number of zeros of non-analytic random signals
Jürgen Angst, Thibault Pautrel, Guillaume Poly
We study the asymptotics as goes to infinity of , the expected number of zeros in of a random periodic signal of…
Riemannian Stochastic Optimization for Sufficient Dimension Reduction
Thibault Pautrel, François Portier
Sufficient dimension reduction (SDR) makes high-dimensional regression tractable by projecting the covariates onto a low-dimensional subspace that preserves the conditional mean of…
FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet
Thibault Pautrel, Florent Bouchard, Ammar Mian +1
We introduce two federated learning frameworks for the classical SPDnet model operating on symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. Unlike st…
Real zeros of random trigonometric polynomials with dependent coefficients
Jürgen Angst, Thibault Pautrel, Guillaume Poly
We further investigate the relations between the large degree asymptotics of the number of real zeros of random trigonometric polynomials with dependent coefficients and the underl…
New asymptotics for the mean number of zeros of random trigonometric polynomials with strongly dependent Gaussian coefficients
Thibault Pautrel
We consider random trigonometric polynomials of the form \[ f_n(t):=\frac{1}{\sqrt{n}} \sum_{k=1}^{n}a_k \cos(k t)+b_k \sin(k t), \] where and a…