arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.10065math.OC
收藏

一种高效的随机微分方程高维梯度估计器

An Efficient High-Dimensional Gradient Estimator for Stochastic Differential Equations

Shengbo Wang, Jose Blanchet, Peter Glynn

AI总结:

本文提出了一种新颖的无偏随机梯度估计器——生成器梯度估计器,用于高维参数化随机微分方程,其计算时间在高维参数下保持稳定,并在高维神经网络参数化的线性二次控制问题中显著提升了效率。

摘要:

过参数化随机微分方程(SDE)模型在多种复杂环境中取得了显著成功,如PDE约束优化、随机控制与强化学习、金融工程以及神经SDEs。这些模型通常具有由高维向量$θ\in \mathbb{R}^n$参数化的系统演化系数,旨在通过随机梯度上升来优化SDE的期望,例如价值函数。因此,设计计算复杂度随$n$良好扩展的高效梯度估计器具有重要意义。本文提出了一种新颖的无偏随机梯度估计器——生成器梯度估计器——其计算时间在$n$上保持稳定。除了确立我们方法对带跳的一般SDE的有效性外,我们还进行了数值实验,在由高维神经网络参数化的线性二次控制问题中测试了我们的估计器。结果表明,与广泛使用的路径微分方法相比,效率有显著提高:我们的估计器实现了近乎恒定的计算时间,随着$n$的增加越来越优于对应方法,并且在不牺牲估计方差的情况下做到这一点。这些实证发现突显了我们提出的方法在优化当代应用中的SDEs的潜力。

英文摘要:

Overparameterized stochastic differential equation (SDE) models have achieved remarkable success in various complex environments, such as PDE-constrained optimization, stochastic control and reinforcement learning, financial engineering, and neural SDEs. These models often feature system evolution coefficients that are parameterized by a high-dimensional vector $θ\in \mathbb{R}^n$, aiming to optimize expectations of the SDE, such as a value function, through stochastic gradient ascent. Consequently, designing efficient gradient estimators for which the computational complexity scales well with $n$ is of significant interest. This paper introduces a novel unbiased stochastic gradient estimator--the generator gradient estimator--for which the computation time remains stable in $n$. In addition to establishing the validity of our methodology for general SDEs with jumps, we also perform numerical experiments that test our estimator in linear-quadratic control problems parameterized by high-dimensional neural networks. The results show a significant improvement in efficiency compared to the widely used pathwise differentiation method: Our estimator achieves near-constant computation times, increasingly outperforms its counterpart as $n$ increases, and does so without compromising estimation variance. These empirical findings highlight the potential of our proposed methodology for optimizing SDEs in contemporary applications.

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。

↑