Score-based constrained generative modeling via Langevin diffusions with boundary conditions
By: Adam Nordenhög, Akash Sharma
Potential Business Impact:
Makes AI create images that follow rules.
Score-based generative models based on stochastic differential equations (SDEs) achieve impressive performance in sampling from unknown distributions, but often fail to satisfy underlying constraints. We propose a constrained generative model using kinetic (underdamped) Langevin dynamics with specular reflection of velocity on the boundary defining constraints. This results in piecewise continuously differentiable noising and denoising process where the latter is characterized by a time-reversed dynamics restricted to a domain with boundary due to specular boundary condition. In addition, we also contribute to existing reflected SDEs based constrained generative models, where the stochastic dynamics is restricted through an abstract local time term. By presenting efficient numerical samplers which converge with optimal rate in terms of discretizations step, we provide a comprehensive comparison of models based on confined (specularly reflected kinetic) Langevin diffusion with models based on reflected diffusion with local time.
Similar Papers
Wasserstein Convergence of Critically Damped Langevin Diffusions
Statistics Theory
Makes AI create better pictures by adding noise.
A Score-based Diffusion Model Approach for Adaptive Learning of Stochastic Partial Differential Equation Solutions
Computation
Helps predict changing weather and science.
Data-driven generative simulation of SDEs using diffusion models
Machine Learning (CS)
Creates realistic data for smarter money decisions.