Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking
Ziyue Wang, Takafumi Kanamori
stat.ML, cs.LG
Submitted: 2026-08-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Dirichlet Diffusion Score Model for Biological Sequence Generation
- Riemannian Score-Based Generative Modelling
- Constrained Synthesis with Projected Diffusion Models
- Reflected Schr\"odinger Bridge for Constrained Generative Modeling
- Diffusion Models for Constrained Domains
- Metropolis Sampling for Constrained Diffusion Models
- Denoising Diffusion Probabilistic Models
- Riemannian Diffusion Models
- Constrained Diffusion Models via Dual Training
- Mirror Diffusion Models for Constrained and Watermarked Generation
- Estimating Density Models with Truncation Boundaries using Score Matching
- Reflected Diffusion Models
- Score-based constrained generative modeling via Langevin diffusions with boundary conditions
- Score matching for compositional distributions
- Generative Modeling by Estimating Gradients of the Data Distribution
- Score-Based Generative Modeling through Stochastic Differential Equations
- Dirichlet Flow Matching with Applications to DNA Sequence Design
- Score Matching for Truncated Density Estimation on a Manifold
- Reflected Flow Matching
- Generalized Score Matching for Non-Negative Data
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches