1 citations · 1 across the 3 of their papers we have counts for
7 papers · 1 filter
Surrogate to Poincaré inequalities on manifolds for structured dimension reduction in nonlinear feature spaces
Alexandre Pasco, Anthony Nouy
This paper is concerned with the approximation of continuously differentiable functions with high-dimensional input by a composition of two functions: a feature map that extracts f…
Approximation and learning with compositional tensor trains
Martin Eigel, Charles Miranda, Anthony Nouy +1
We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train form…
Surrogate to Poincaré inequalities on manifolds for dimension reduction in nonlinear feature spaces
Anthony Nouy, Alexandre Pasco
We aim to approximate a continuously differentiable function by a composition of functions where $g:\mathbb{R}^d \rightarrow \mat…
Nonlinear manifold approximation using compositional polynomial networks
Antoine Bensalah, Anthony Nouy, Joel Soffo
We consider the problem of approximating a subset of a Hilbert space by a low-dimensional manifold , using samples from . We propose a nonlinear approximation metho…
Moment-SoS Methods for Optimal Transport Problems
Olga Mula, Anthony Nouy
Most common Optimal Transport (OT) solvers are currently based on an approximation of underlying measures by discrete measures. However, it is sometimes relevant to work only with…
Active learning of tree tensor networks using optimal least-squares
Cécile Haberstich, Anthony Nouy, Guillaume Perrin
In this paper, we propose new learning algorithms for approximating high-dimensional functions using tree tensor networks in a least-squares setting. Given a dimension tree or arch…