arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.22265cs.LGcs.CV
收藏

熵控流匹配

Entropy-Controlled Flow Matching

William & Mary(威廉与玛丽学院)

Chika Maduabuchi

AI总结:

提出熵控流匹配(ECFM),通过约束连续方程路径的全局熵率,避免低熵瓶颈导致的语义模式丢失,并证明其与薛定谔桥的联系及最优传输收敛性。

摘要:

现代视觉生成器通过时间索引测度将基础分布传输到数据,实现为确定性流(ODE)或随机扩散(SDE)。尽管经验性能强劲,标准流匹配目标不直接控制轨迹的信息几何,允许低熵瓶颈暂时耗尽语义模式。我们提出熵控流匹配(ECFM):一个在连续方程路径上的约束变分原理,强制执行全局熵率预算 d/dt H(mu_t) >= -lambda。ECFM 是 Wasserstein 空间中的凸优化,具有 KKT/Pontryagin 系统,并允许等价于具有显式熵乘子的薛定谔桥的随机控制表示。在纯传输机制中,ECFM 恢复熵最优传输测地线,并在 lambda -> 0 时 Gamma-收敛到经典 OT。我们进一步获得证书式模式覆盖和密度下限保证,具有 Lipschitz 稳定性,并为无约束流匹配构建了近最优的崩溃反例。

英文摘要:

Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry of the trajectory, allowing low-entropy bottlenecks that can transiently deplete semantic modes. We propose Entropy-Controlled Flow Matching (ECFM): a constrained variational principle over continuity-equation paths enforcing a global entropy-rate budget d/dt H(mu_t) >= -lambda. ECFM is a convex optimization in Wasserstein space with a KKT/Pontryagin system, and admits a stochastic-control representation equivalent to a Schrodinger bridge with an explicit entropy multiplier. In the pure transport regime, ECFM recovers entropic OT geodesics and Gamma-converges to classical OT as lambda -> 0. We further obtain certificate-style mode-coverage and density-floor guarantees with Lipschitz stability, and construct near-optimal collapse counterexamples for unconstrained flow matching.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑