4 papers
Influence as soft sparsity: Estimation of monotone functions on
Gérard Biau
We study the problem of estimating a monotone function from noisy observations at uniformly random vertices of the Boolean hypercube. As a measure of complexi…
A Geometry-Aware Residual Correction of Hagan's SABR Implied Volatility Formula
Adil Reghai, Lama Tarsissi, Gérard Biau +1
This paper proposes a hybrid methodology to improve the approximation of SABR (Stochastic Alpha Beta Rho) implied volatility by combining analytical structure with machine learning…
On the convergence of PINNs
Nathan Doumèche, Gérard Biau, Claire Boyer
Physics-informed neural networks (PINNs) are a promising approach that combines the power of neural networks with the interpretability of physical modeling. PINNs have shown good p…
Scaling ResNets in the Large-depth Regime
Pierre Marion, Adeline Fermanian, Gérard Biau +1
Deep ResNets are recognized for achieving state-of-the-art results in complex machine learning tasks. However, the remarkable performance of these architectures relies on a trainin…