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 2012.04827math.OC
收藏

基于一致性的自适应动量估计全局最优化方法

A consensus-based global optimization method with adaptive momentum estimation

Jingrun Chen, Shi Jin, Liyao Lyu

摘要:

大规模机器学习和人工智能应用中的目标函数通常存在于具有强非凸性和大量局部极小值的高维空间中。一阶方法,如随机梯度法和亚当,经常被用来寻找全局最小值。近年来,基于一致性的优化方法(CBO)作为一种无梯度最优化方法被引入,并证明了其收敛性。通过将各向同性的几何布朗运动替换为分量运动,CBO方法的最新改进保证收敛到具有维数无关参数的全局极小点,尽管初始数据需要很好地选择。本文在CBO方法和Adam的基础上,提出了一种基于共识的自适应动量估计全局最优化方法(Adam-CBO)。Adam-CBO方法的优点包括:(1)能够以高成功率和低成本找到非凸目标函数的全局最小值;(2)可以处理不可微的激活函数,从而以更好的精度逼近低正则性函数。前者是通过近似的$1000$维Rastrigin功能与$100\%$成功率在成本只线性增长的维度。后者通过求解具有低正则性解的偏微分方程的机器学习任务来证实,其中Adam-CBO方法提供了比最先进的方法Adam更好的结果。一个线性稳定性分析,以了解渐近行为的Adam-CBO方法。

英文摘要:

Objective functions in large-scale machine-learning and artificial intelligence applications often live in high dimensions with strong non-convexity and massive local minima. First-order methods, such as the stochastic gradient method and Adam, are often used to find global minima. Recently, the consensus-based optimization (CBO) method has been introduced as one of the gradient-free optimization methods and its convergence is proven with dimension-dependent parameters, which may suffer from the curse of dimensionality. By replacing the isotropic geometric Brownian motion with the component-wise one, the latest improvement of the CBO method is guaranteed to converge to the global minimizer with dimension-independent parameters, although the initial data need to be well-chosen. In this paper, based on the CBO method and Adam, we propose a consensus-based global optimization method with adaptive momentum estimation (Adam-CBO). Advantages of the Adam-CBO method include: (1) capable of finding global minima of non-convex objective functions with high success rates and low costs; (2) can handle non-differentiable activation functions and thus approximate low-regularity functions with better accuracy. The former is verified by approximating the $1000$ dimensional Rastrigin function with $100\%$ success rate at a cost only growing linearly with respect to the dimensionality. The latter is confirmed by solving a machine learning task for partial differential equations with low-regularity solutions where the Adam-CBO method provides better results than the state-of-the-art method Adam. A linear stability analysis is provided to understand the asymptotic behavior of the Adam-CBO method.

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。

↑