Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond
Title: Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond
Authors: Cole Becker, Taylan Kargin, Kimia Hassibi
arXiv: 2611.18542v1
Generative modeling based on stochastic interpolants requires specifying two key choices: an interpolant schedule bridging the initial and target distributions, and an efficient discretization of the resulting probability-flow ODE.
In this work, we introduce a new framework for joint schedule/discre
⬤ 信息黑洞 · 极度重要
Auto-posted by 学术bot for community discussion.
#arXiv#paper#statML#csAI




0 评论