arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00634math.OCcs.ITmath.ITquant-ph
收藏

通过后验认证的向量场实现确定性零阶镜像下降

Trajectory-Wise Certification for Vector-Field Mirror Descent with Deterministic Finite Differences

School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);International Quantum Academy(国际量子科学院);Graduate School of Mathematics, Nagoya University(名古屋大学大学院数学研究科)

Masahito Hayashi

AI总结:

本文提出了一种确定性零阶镜像下降框架,通过向量场实现后验认证,结合有限差分方法和广义星凸性条件,揭示了零阶镜像下降中的几何结构。

摘要:

我们通过将梯度替换为一般向量场,开发了一种确定性零阶镜像下降框架,从而得到由向量场驱动的镜像更新,该更新在保持Bregman几何的同时,能够容纳无导数 oracle。我们的分析提供了一个统一的评估模板,用于在相对光滑性型不等式下对最后迭代函数值进行评估,重点在于轨迹层面(后验)的认证:只要在实际迭代过程中可验证的不等式成立,我们就能获得显式的最后迭代保证。该框架涵盖了广泛的信息几何算法,包括广义Blahut-Arimoto型更新,通过合适选择向量场表达其动态。然后,我们通过确定性的中心有限差分在中等维度中实例化该理论,其中通过确定性的中心有限差分构造向量场需要2d个非中心函数值(和一个可重复使用的中心值),即总共2d+1次评估,其中d是输入实数的数量。在确定性的有限差分设置中,关键接口性质不是传统的凸性本身,而是一种带孔邻域广义星凸性条件,该条件隔离了一个显式的分辨率相关的误差下限。为有限差分向量场建立这一属性归结为一个稳健的锥支配设计问题;我们给出一个显式的缩放规则,以确保在圆锥上的所需统一支配。这些结果揭示了零阶镜像下降中隐藏的几何结构,将Bregman折叠恒等式、确定性认证和稳健的锥几何联系起来。

英文摘要:

We study mirror descent in which the objective gradient is replaced by a general vector field. Since such a field does not automatically relate the mirror update to the objective gap, we introduce a trajectory-wise generalized relative-smoothness condition and a generalized star-convexity interface. Together they yield a finite-horizon, a posteriori last-iterate certificate with an accumulated-stepsize term and an exceptional-region-dependent error term. We also give a pointwise sufficient condition for positive admissible stepsizes, displaying the effects of objective smoothness, mirror-map conditioning, and vector-field mismatch. We then construct a deterministic zeroth-order instance from coordinate central differences. The function values place the unknown gradient in an explicit uncertainty box, and verification of the interface reduces to robust conic dominance. We derive an explicit scaling of the central-difference vector that guarantees the required dominance over the gradient uncertainty set. Under uniform Hessian bounds, the resulting vector field satisfies the interface outside an explicit resolution-dependent neighborhood. The final guarantee combines a rate term governed by accumulated accepted stepsizes with a finite-resolution error floor.

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。

↑