arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.02676math.OCmath.DS
收藏

通过带有隐式 Hessian 阻尼和 Tikhonov 正则化的二阶动力系统求解凸优化问题

Solving convex optimization problems via a second order dynamical system with implicit Hessian damping and Tikhonov regularization

Szilárd Csaba László

AI总结:

本文研究带有 Tikhonov 正则化项和隐式 Hessian 阻尼的二阶动力系统,用于凸 Fréchet 可微函数的最小化问题,通过显式离散化获得梯度型惯性算法,并证明了轨迹对全局最小值及极小值点的弱或强收敛性。

摘要:

本文研究了一个带有 Tikhonov 正则化项的二阶动力系统,用于解决凸 Fréchet 可微函数的最小化问题。除了渐近消失的阻尼外,我们还考虑了所研究动力系统中的隐式 Hessian 驱动阻尼,这使得我们能够通过直接显式离散化获得梯度型惯性算法。我们证明了在生成轨迹中目标函数的值快速收敛到目标函数的全局最小值,并且根据 Tikhonov 正则化参数,生成的轨迹弱收敛到目标函数的一个极小值点,或者生成的轨迹强收敛到目标函数 $\argmin$ 集合中范数最小的元素。我们还获得了速度向零的快速收敛性以及一些积分估计。我们的分析表明,Tikhonov 正则化参数与阻尼参数高度相关,存在一种参数设置能够区分轨迹弱收敛到极小值点与轨迹强收敛到最小范数极小值点这两种情形。

英文摘要:

This paper deals with a second order dynamical system with a Tikhonov regularization term in connection to the minimization problem of a convex Fréchet differentiable function. The fact that beside the asymptotically vanishing damping we also consider an implicit Hessian driven damping in the dynamical system under study allows us, via straightforward explicit discretization, to obtain inertial algorithms of gradient type. We show that the value of the objective function in a generated trajectory converges rapidly to the global minimum of the objective function and depending the Tikhonov regularization parameter the generated trajectory converges weakly to a minimizer of the objective function or the generated trajectory converges strongly to the element of minimal norm from the $\argmin$ set of the objective function. We also obtain the fast convergence of the velocities towards zero and some integral estimates. Our analysis reveals that the Tikhonov regularization parameter and the damping parameters are strongly correlated, there is a setting of the parameters that separates the cases when weak convergence of the trajectories to a minimizer and strong convergence of the trajectories to the minimal norm minimizer can be obtained.

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。

↑