כתבה
arXiv cs.LG ·
Diffusion לפיזיקה: פיתוח ניהול סדר תלוי-אחורה לפיזור
Backward SDEs-based Diffusion for Physics-Constrained Generation
פיתוח ניהול סדר תלוי-אחורה לפיזור, שמספק פיזור תלוי-אחורה שמבטיח תכונות פיזיקליות.
תקציר מקורי באנגליתarXiv:2609.15702v1 Announce Type: new Abstract: Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is often handled by heuristic guidance, intermittent projections, or task-specific conditional training, with limited guarantees of feasibility at the end of inference. We propose terminal-conditioned inversion for score-based SDE priors. Given a frozen Score-SDE prior and a task-defined terminal feasibility specification, we construct an associated backward stochastic differential equation whose adapted solution defines a principled inverse map from the terminal requirement to a prior state at a chosen noise level. Under standard regularity conditions, we establish existence and uniqueness of the a
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית