跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.18542 · v1

Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond

首次提交 2026-11-14 02:49
版本更新 2026-11-14 02:49
雷达观测 2026-11-16 13:44
arXiv ↗PDF ↗

摘要

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/discretization design based on the analyticity properties of the (complexified) ODE trajectories, which in turn ensure good numerical behavior. Our formulation can be solved exactly via conformal mapping, yielding a natural family of variance-preserving elliptic schedules, parametrized by Jacobi elliptic functions. Pairing an elliptic schedule with a tailored discretization, we obtain Zoloflow, a new sampling algorithm closely connected to Zolotarev's optimal rational function approximants. Crucially, both the elliptic schedule and Zoloflow explicitly incorporate the condition number κκ of the target distribution and reduce to the classical trig schedule in the limit κ→1κ\rightarrow 1. For Gaussian targets, Zoloflow achieves minimax optimality among all oblivious score-span algorithms, attaining total-variation error ε\varepsilon using Θ(log⁡κ log⁡(d/ε))Θ(\logκ\,\log(\sqrt d/\varepsilon)) (exact) score queries. For the log-concave case, the elliptic schedule allows sampling with at most ε\varepsilon 2-Wasserstein-error by requiring merely O~(d polylog(κ,1/ε))\widetilde{O}(\sqrt{d} \, \mathrm{polylog}(κ, 1/\varepsilon)) score evaluations. Complementing these theoretical results, we empirically evaluate the elliptic schedule on general (non-log-concave) target distributions, including detailed comparisons with alternative schedule proposals on both synthetic benchmarks and existing image generation datasets.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-14 02:49 · 最新观测版本

Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond

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/discretization design based on the analyticity properties of the (complexified) ODE trajectories, which in turn ensure good numerical behavior. Our formulation can be solved exactly via conformal mapping, yielding a natural family of variance-preserving elliptic schedules, parametrized by Jacobi elliptic functions. Pairing an elliptic schedule with a tailored discretization, we obtain Zoloflow, a new sampling algorithm closely connected to Zolotarev's optimal rational function approximants. Crucially, both the elliptic schedule and Zoloflow explicitly incorporate the condition number κκ of the target distribution and reduce to the classical trig schedule in the limit κ→1κ\rightarrow 1. For Gaussian targets, Zoloflow achieves minimax optimality among all oblivious score-span algorithms, attaining total-variation error ε\varepsilon using Θ(log⁡κ log⁡(d/ε))Θ(\logκ\,\log(\sqrt d/\varepsilon)) (exact) score queries. For the log-concave case, the elliptic schedule allows sampling with at most ε\varepsilon 2-Wasserstein-error by requiring merely O~(d polylog(κ,1/ε))\widetilde{O}(\sqrt{d} \, \mathrm{polylog}(κ, 1/\varepsilon)) score evaluations. Complementing these theoretical results, we empirically evaluate the elliptic schedule on general (non-log-concave) target distributions, including detailed comparisons with alternative schedule proposals on both synthetic benchmarks and existing image generation datasets.

查看此版本解读 →查看此版本原文 ↗