Portrait de Danyal REHMAN n'est pas disponible

Danyal REHMAN

Postdoctorat - UdeM
Superviseur⋅e principal⋅e
Sujets de recherche
Apprentissage de représentations
Apprentissage par renforcement
Apprentissage profond
Modèles génératifs
Modélisation moléculaire

Publications

FALCON: Few-step Accurate Likelihoods for Continuous Flows
Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
Oscar Davis
Michael Bronstein
Avishek Joey Bose
Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large… (voir plus)-scale diffusion and flow matching models. However, such modern generative models suffer from expensive inference, inhibiting their use in numerous scientific applications like Boltzmann Generators (BGs) for molecular conformations that require fast likelihood evaluation. In this paper, we revisit classical normalizing flows in the context of BGs that offer efficient sampling and likelihoods, but whose training via maximum likelihood is often unstable and computationally challenging. We propose Regression Training of Normalizing Flows (RegFlow), a novel and scalable regression-based training objective that bypasses the numerical instability and computational challenge of conventional maximum likelihood training in favour of a simple