708 citations · 2.8k across the 48 of their papers we have counts for
51 papers
Path Shadowing Monte-Carlo
Rudy Morel, Stéphane Mallat, Jean-Philippe Bouchaud
We introduce a Path Shadowing Monte-Carlo method, which provides prediction of future paths, given any generative model. At any given date, it averages future quantities over gener…
Scattering Spectra Models for Physics
Sihao Cheng, Rudy Morel, Erwan Allys +2
Physicists routinely need probabilistic models for a number of tasks such as parameter inference or the generation of new realizations of a field. Establishing such models for high…
Conditionally Strongly Log-Concave Generative Models
Florentin Guth, Etienne Lempereur, Joan Bruna +1
There is a growing gap between the impressive results of deep image generative models and classical algorithms that offer theoretical guarantees. The former suffer from mode collap…
A Rainbow in Deep Network Black Boxes
Florentin Guth, Brice Ménard, Gaspar Rochette +1
A central question in deep learning is to understand the functions learned by deep networks. What is their approximation class? Do the learned weights and representations depend on…
Learning multi-scale local conditional probability models of images
Zahra Kadkhodaie, Florentin Guth, Stéphane Mallat +1
Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods. But th…
Wavelet Score-Based Generative Modeling
Florentin Guth, Simon Coste, Valentin De Bortoli +1
Score-based generative models (SGMs) synthesize new data samples from Gaussian white noise by running a time-reversed Stochastic Differential Equation (SDE) whose drift coefficient…