Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their values ...

Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models that would otherwise be intractable. However, its formulation depends on expec...

This monograph presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffu...

Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical inference. Classical approaches such as molecular dynamics or Markov chain...

A hands-on tutorial with Python and CasADi

An analysis that draws on nonequilibrium thermodynamics shows that thermodynamic dissipation limits data quality in diffusion models and that optimal transport dynamics yields more accurate generation...

Density ratio estimation in high dimensions can be reframed as integrating a certain quantity, the time score, over probability paths which interpolate between the two densities. In practice, the time...

YouTube video by LoG Meetup NYC

Diffusion models are powerful generative frameworks that iteratively denoise white noise into structured data via learned score functions. Through theory and experiments, we demonstrate that these sco...