A. Nouy

collaborators

12 papers

cs.LG2026

Natural gradient descent with momentum

Anthony Nouy, AgustÃn Somacal

We consider the problem of approximating a function by an element of a nonlinear manifold which admits a differentiable parametrization, typical examples being neural networks with…

math.NA2026

Random sketching of operators with application to learning preconditioners

Oleg Balabanov, Anthony Nouy, Alexandre Pasco

We propose a new random sketching approach for embedding high-dimensional Hilbert-Schmidt operators, using random input-output pairs. Such operator can then be approximated in a lo…

math.NA2026

Surrogate to PoincarÃ© 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…

math.NA2026

Surrogate to PoincarÃ© inequalities on manifolds for dimension reduction in nonlinear feature spaces

Anthony Nouy, Alexandre Pasco

We aim to approximate a continuously differentiable function $u : R^{d} \to R$ by a composition of functions $f \circ g$ where $g:\mathbb{R}^d \rightarrow \mat…

math.OC2026

Optimal sampling for stochastic and natural gradient descent

Robert Gruhlke, Anthony Nouy, Philipp Trunschke

We consider the problem of optimising the expected value of a loss functional over a nonlinear model class of functions, assuming that we have only access to realisations of the gr…

math.NA2026

Boosted optimal weighted least-squares

This paper is concerned with the approximation of a function $u$ in a given approximation space $V_{m}$ of dimension $m$ from evaluations of the function at $n$ suitably chosen point…