arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09431math.STcs.IThep-thmath.ITmath.OCstat.MLstat.TH
收藏

统计流形上概率的拉格朗日和哈密顿力学

Lagrangian and Hamiltonian Mechanics for Probabilities on the Statistical Manifold

Goffredo Chirco, Luigi Malagò, Giovanni Pistone

摘要:

我们在概率分布的黎曼流形上给出了经典力学的信息几何公式,黎曼流形是一个具有对偶平坦连接的仿射流形。在一个非参数的形式主义,我们认为一个有限的样本空间上的正概率函数的完整的集合,我们提供了一个具体的表达的正切和余切空间的统计流形,在希尔伯特束结构,我们称之为统计束。在这种情况下,我们计算的速度和加速度的一维统计模型使用的典型的对偶对平行运输和定义一个连贯的形式主义的拉格朗日和哈密顿力学束。最后,在一系列的例子中,我们展示了我们的形式主义如何提供了一个一致的框架,加速自然梯度动力学的概率单纯形,铺平了道路,直接应用于优化,对策论和神经网络。

英文摘要:

We provide an Information-Geometric formulation of Classical Mechanics on the Riemannian manifold of probability distributions, which is an affine manifold endowed with a dually-flat connection. In a non-parametric formalism, we consider the full set of positive probability functions on a finite sample space, and we provide a specific expression for the tangent and cotangent spaces over the statistical manifold, in terms of a Hilbert bundle structure that we call the Statistical Bundle. In this setting, we compute velocities and accelerations of a one-dimensional statistical model using the canonical dual pair of parallel transports and define a coherent formalism for Lagrangian and Hamiltonian mechanics on the bundle. Finally, in a series of examples, we show how our formalism provides a consistent framework for accelerated natural gradient dynamics on the probability simplex, paving the way for direct applications in optimization, game theory and neural networks.

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。

↑