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 2409.10664math.OCcs.SYeess.SPeess.SY
收藏

近端梯度动力学:单调性、指数收敛与应用

Proximal Gradient Dynamics: Monotonicity, Exponential Convergence, and Applications

Anand Gokhale, Alexander Davydov, Francesco Bullo

AI总结:

本文研究近端梯度动力学,证明代价函数沿轨迹单调递减,提出保证指数收敛的新条件并证明其蕴含近端 Polyak-Łojasiewicz 条件,同时将结果扩展到时变优化问题,并应用于 LASSO、矩阵问题及前馈神经网络实验。

摘要:

本文研究近端梯度动力学。这种最近提出的连续时间动力学用于求解代价函数可分离为非光滑凸分量和光滑分量的优化问题。首先,我们证明代价函数沿近端梯度动力学的轨迹单调递减。然后,我们引入一个新的条件,保证代价函数指数收敛到其最优值,并证明该条件蕴含近端 Polyak-Łojasiewicz 条件。我们还证明近端 Polyak-Łojasiewicz 条件保证代价函数的指数收敛。此外,我们将这些结果扩展到时变优化问题,为平衡跟踪提供界。最后,我们讨论这些发现的应用,包括 LASSO 问题、某些基于矩阵的问题以及一个前馈神经网络的数值实验。

英文摘要:

In this letter we study the proximal gradient dynamics. This recently-proposed continuous-time dynamics solves optimization problems whose cost functions are separable into a nonsmooth convex and a smooth component. First, we show that the cost function decreases monotonically along the trajectories of the proximal gradient dynamics. We then introduce a new condition that guarantees exponential convergence of the cost function to its optimal value, and show that this condition implies the proximal Polyak-Łojasiewicz condition. We also show that the proximal Polyak-Łojasiewicz condition guarantees exponential convergence of the cost function. Moreover, we extend these results to time-varying optimization problems, providing bounds for equilibrium tracking. Finally, we discuss applications of these findings, including the LASSO problem, certain matrix based problems and a numerical experiment on a feed-forward neural network.

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。

↑