arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.07013math.OCcs.NAmath.NA
收藏

Optimization与非局部微积分学习

Optimization and Learning With Nonlocal Calculus

Sriram Nagaraj

摘要:

非局部模型最近在非线性连续介质力学中产生了重大影响,并被用来描述物理系统/过程,这些物理系统/过程不能被经典的基于微积分的“局部”方法准确描述。在某种程度上,这是由于它们的多尺度性质,使微观层面的行为聚集,以获得一个宏观层面的描述奇异/不规则现象,如peridemics,裂纹扩展,异常扩散和运输现象。这些模型的核心是非局部微分算子,包括梯度/海森函数的非局部模拟。本文首次使用这种非局部运营商的优化和学习的背景下。在欧几里得空间上定义并分析了(随机)梯度下降法和牛顿法的非局部模拟的收敛性质。我们的研究结果表明,作为非局部相互作用变得不那么明显,对应于非局部优化的最优收敛到“通常”的最优。同时,我们认为,非局部学习是可能的情况下,标准微积分失败。作为一个程式化的数值例子,我们考虑的问题,不可微的参数估计的非光滑的翻译流形,并表明我们的非局部梯度下降恢复未知的翻译参数从一个不可微的目标函数。

英文摘要:

Nonlocal models have recently had a major impact in nonlinear continuum mechanics and are used to describe physical systems/processes which cannot be accurately described by classical, calculus based "local" approaches. In part, this is due to their multiscale nature that enables aggregation of micro-level behavior to obtain a macro-level description of singular/irregular phenomena such as peridynamics, crack propagation, anomalous diffusion and transport phenomena. At the core of these models are nonlocal differential operators, including nonlocal analogs of the gradient/Hessian. This paper initiates the use of such nonlocal operators in the context of optimization and learning. We define and analyze the convergence properties of nonlocal analogs of (stochastic) gradient descent and Newton's method on Euclidean spaces. Our results indicate that as the nonlocal interactions become less noticeable, the optima corresponding to nonlocal optimization converge to the "usual" optima. At the same time, we argue that nonlocal learning is possible in situations where standard calculus fails. As a stylized numerical example of this, we consider the problem of non-differentiable parameter estimation on a non-smooth translation manifold and show that our nonlocal gradient descent recovers the unknown translation parameter from a non-differentiable objective function.

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。

↑