4 papers
Generative Modeling via Kernelized Stochastic Interpolants
Florentin Coeurdoux, Etienne Lempereur, Nathanaël Cuvelle-Magar +2
We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative S…
MGD: Moment Guided Diffusion for Maximum Entropy Generation
Etienne Lempereur, Nathanaël Cuvelle--Magar, Florentin Coeurdoux +2
Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from…
Hierarchic Flows to Estimate and Sample High-dimensional Probabilities
Etienne Lempereur, Stéphane Mallat
Finding low-dimensional interpretable models of complex physical fields such as turbulence remains an open question, 80 years after the pioneer work of Kolmogorov. Estimating high-…
Effective Energy, Interactions And Out Of Equilibrium Nature Of Scalar Active Matter
Antonin Brossollet, Etienne Lempereur, Stéphane Mallat +1
Estimating the effective energy, of a stationary probability distribution is a challenge for non-equilibrium steady states. Its solution could offer a novel framewor…