arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.09249math.OC
收藏

高维机器学习问题的一种基于共识的全局最优化方法

A consensus-based global optimization method for high dimensional machine learning problems

José A. Carrillo, Shi Jin, Lei Li, Yuhua Zhu

摘要:

本文改进了最近提出的基于共识的最优化方法。平瑙角托策克岛Tse和S. Martin,数学模型方法应用科学,27(01):183--204,2017],其是用于一般非凸函数的无梯度最优化方法。我们首先用分量布朗运动代替各向同性几何布朗运动,从而消除了漂移率的维数依赖性,使得该方法在高维最优化问题中更具竞争力.其次,我们利用随机小批量的思想,以减少计算加权平均的计算成本,个别粒子倾向于放松。对于它的平均场极限-一个非线性福克-普朗克方程-我们证明,在时间连续和半离散设置,该方法的收敛性,这是指数的时间,保证与参数约束{ \it独立}的维数。我们还对高维问题进行了数值试验,以检验该方法的成功率。

英文摘要:

We improve recently introduced consensus-based optimization method, proposed in [R. Pinnau, C. Totzeck, O. Tse and S. Martin, Math. Models Methods Appl. Sci., 27(01):183--204, 2017], which is a gradient-free optimization method for general non-convex functions. We first replace the isotropic geometric Brownian motion by the component-wise one, thus removing the dimensionality dependence of the drift rate, making the method more competitive for high dimensional optimization problems. Secondly, we utilize the random mini-batch ideas to reduce the computational cost of calculating the weighted average which the individual particles tend to relax toward. For its mean-field limit--a nonlinear Fokker-Planck equation--we prove, in both time continuous and semi-discrete settings, that the convergence of the method, which is exponential in time, is guaranteed with parameter constraints {\it independent} of the dimensionality. We also conduct numerical tests to high dimensional problems to check the success rate of the 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。

↑