arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.25822math.OCcs.SYeess.SY
收藏

关于满足广义Łojasiewicz不等式的梯度流的增量性和半全局指数稳定性

On incremental and semi-global exponential stability of gradient flows satisfying generalized Łojasiewicz inequalities

ECE Department at Northeastern University(东北大学电气与计算机工程系)

Andreas Oliveira, Arthur C. B. de Oliveira, Mario Sznaier, Eduardo Sontag

AI总结:

本文基于收缩理论,研究满足广义Łojasiewicz不等式的梯度系统,证明在目标函数有唯一强凸极小值时,系统具有半全局指数稳定性,并给出非凸梯度流的全局增量性指数稳定条件。

摘要:

Łojasiewicz不等式刻画了梯度流沿目标值的收敛性,并在某些特殊情况下导致成本的指数衰减。然而,此类结果无法直接给出状态的收敛率。本文利用收缩理论,推导出满足广义Łojasiewicz不等式的梯度系统在状态空间中的保证。我们首先证明,当目标函数有唯一强凸极小值时,广义Łojasiewicz不等式暗示半全局指数稳定性;在任意紧致子集上,这导致指数稳定性。然后,我们给出两个基于曲率的充分条件,以及对Łojasiewicz速率的约束,使得非凸梯度流在全局范围内具有增量性指数稳定性。

英文摘要:

The Łojasiewicz inequality characterizes objective-value convergence along gradient flows and, in special cases, yields exponential decay of the cost. However, such results do not directly give rates of convergence in the state. In this paper, we use contraction theory to derive state-space guarantees for gradient systems satisfying generalized Łojasiewicz inequalities. We first show that, when the objective has a unique strongly convex minimizer, the generalized Łojasiewicz inequality implies semi-global exponential stability; on arbitrary compact subsets, this yields exponential stability. We then give two curvature-based sufficient conditions, together with constraints on the Łojasiewicz rate, under which the nonconvex gradient flow is globally incrementally exponentially stable.

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。

↑