Gérard Biau

Approximating Lipschitz continuous functions with GroupSort neural networks

2020 · arXiv (Cornell University)

Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants. Motivated by these observations, we study the recently introduced GroupSort neural networks, with constraints on the …

Physics-informed kernel learning

2024 · arXiv (Cornell University)

Physics-informed machine learning typically integrates physical priors into the learning process by minimizing a loss function that includes both a data-driven term and a partial differential equation (PDE) regularization. Building on the formulation of the …

Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization

2025 · arXiv (Cornell University)

Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples replicate the training data. …