10 papers
Generating Physically Consistent Molecules with Energy-Based Models
Christoph Griesbacher, Lea Bogensperger, Andreas Habring +1
Molecules in equilibrium follow a Boltzmann distribution, making the underlying energy landscape a physically grounded modeling objective. However, such landscapes are difficult to…
Time-Inhomogeneous Preconditioned Langevin Dynamics
Alexander Falk, Laurenz Nagler, Andreas Habring +1
Langevin sampling from distributions of the form faces two major challenges: (global) mode coverage and (local) mode exploration. The first challenge is…
Diffusion at Absolute Zero: Langevin Sampling using Successive Moreau Envelopes [journal paper]
Andreas Habring, Alexander Falk, Martin Zach +1
We propose a method for sampling from Gibbs distributions of the form by considering a family of approximations of the target density which i…
An Inertial Langevin Algorithm
Alexander Falk, Andreas Habring, Christoph Griesbacher +1
We present a novel method for drawing samples from Gibbs distributions with densities of the form . The method accelerates the unadjusted Langevin algori…
Energy-based models for inverse imaging problems
Andreas Habring, Martin Holler, Thomas Pock +1
In this chapter we provide a thorough overview of the use of energy-based models (EBMs) in the context of inverse imaging problems. EBMs are probability distributions modeled via G…
An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation
Lea Bogensperger, Matthias J. Ehrhardt, Thomas Pock +2
We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minim…