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 2102.00810math.OC
收藏

Gauss-Newton方法的柔性修正及其随机推广

Flexible Modification of Gauss-Newton Method and Its Stochastic Extension

Nikita Yudin, Alexander Gasnikov

摘要:

基于解的残差上界和二次正则化思想,提出了一种新的求解非线性方程组的Gauss-Newton方法。我们得到了这种方法的整体收敛界,并在自然非退化的假设下,我们提出了局部平方收敛的结果。我们发展了Gauss-Newton方法的随机最优化算法,并利用弱增长条件(WGC)和Polyak-Lojasiewicz(PL)不等式证明了这些算法的次线性和线性收敛速率。我们证明了在WGC和PL条件下,随机环境下的高斯-牛顿法可以有效地找到与确定性最优化方法的收敛速度相当的解。所提出的方法统一了大多数实际使用的高斯-牛顿法修正,并可以很容易地在它们之间插值,提供了灵活方便的方法,易于使用标准的凸优化技术来实现。

英文摘要:

This work presents a novel version of recently developed Gauss-Newton method for solving systems of nonlinear equations, based on upper bound of solution residual and quadratic regularization ideas. We obtained for such method global convergence bounds and under natural non-degeneracy assumptions we present local quadratic convergence results. We developed stochastic optimization algorithms for presented Gauss-Newton method and justified sub-linear and linear convergence rates for these algorithms using weak growth condition (WGC) and Polyak-Lojasiewicz (PL) inequality. We show that Gauss-Newton method in stochastic setting can effectively find solution under WGC and PL condition matching convergence rate of the deterministic optimization method. The suggested method unifies most practically used Gauss-Newton method modifications and can easily interpolate between them providing flexible and convenient method easily implementable using standard techniques of convex optimization.

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。

↑