Towards predicting equilibrium distributions for molecular systems with deep learning
Advances in deep learning have greatly improved structure prediction of molecules.
However, many macroscopic observations that are important for real-world applications are …
However, many macroscopic observations that are important for real-world applications are …
Score-based diffusion meets annealed importance sampling
More than twenty years after its introduction, Annealed Importance Sampling (AIS) remains
one of the most effective methods for marginal likelihood estimation. It relies on a sequence …
one of the most effective methods for marginal likelihood estimation. It relies on a sequence …
Predicting equilibrium distributions for molecular systems with deep learning
Advances in deep learning have greatly improved structure prediction of molecules.
However, many macroscopic observations that are important for real-world applications are …
However, many macroscopic observations that are important for real-world applications are …
Flow annealed importance sampling bootstrap
Normalizing flows are tractable density models that can approximate complicated target
distributions, eg Boltzmann distributions of physical systems. However, current methods for …
distributions, eg Boltzmann distributions of physical systems. However, current methods for …
Transport meets variational inference: Controlled monte carlo diffusions
Connecting optimal transport and variational inference, we present a principled and
systematic framework for sampling and generative modelling centred around divergences …
systematic framework for sampling and generative modelling centred around divergences …
Adaptive annealed importance sampling with constant rate progress
S Goshtasbpour, V Cohen… - … on Machine Learning, 2023 - proceedings.mlr.press
Abstract Annealed Importance Sampling (AIS) synthesizes weighted samples from an
intractable distribution given its unnormalized density function. This algorithm relies on a …
intractable distribution given its unnormalized density function. This algorithm relies on a …
Langevin diffusion variational inference
T Geffner, J Domke - International Conference on Artificial …, 2023 - proceedings.mlr.press
Many methods that build powerful variational distributions based on unadjusted Langevin
transitions exist. Most of these were developed using a wide range of different approaches …
transitions exist. Most of these were developed using a wide range of different approaches …
Improving mutual information estimation with annealed and energy-based bounds
Mutual information (MI) is a fundamental quantity in information theory and machine
learning. However, direct estimation of MI is intractable, even if the true joint probability …
learning. However, direct estimation of MI is intractable, even if the true joint probability …