Nesterov ODE 在非保守向量场下的不稳定性研究
On the Instability of Nesterov's ODE under Non-Conservative Vector Fields
AI总结:
本研究证明非保守向量场可致 Nesterov ODE 不稳定,提出基于周期重启的混合动力系统,建立重置周期界限以确保 Lyapunov 函数递减,实现加速收敛,数值实验验证了理论。
摘要:
我们研究了 Nesterov ODE 在非保守环境下的不稳定性性质,其中驱动项不一定是势函数的梯度。虽然基于梯度的驱动项的优化设置中,Nesterov ODE 的收敛性质已被充分刻画,但我们表明,任意小的非保守项的存在可能导致不稳定性,这一现象此前在优化和博弈论问题的数值研究中已被经验性地观察到。我们的不稳定性分析结合了多时间尺度技术,例如通过常数变易公式进行平均化,以及 Floquet 理论,重点关注向量场为线性且其 Helmholtz 分解揭示出非零非保守分量的系统。为了解决非零非保守分量下的动力学不稳定性问题,我们研究了一种基于重启的正则化机制。由此产生的系统是一个混合动力系统,在流动区间内镜像 Nesterov ODE,并通过离散周期跳跃实现动量状态的重置。对于该混合系统,我们建立了关于重置周期的新颖显式界限,以确保合适的 Lyapunov 函数的递减,从而在驱动项满足适当的光滑性和强单调性条件下,不仅保证稳定性,还保证“加速”收敛速率。数值模拟支持了我们的理论结果。
英文摘要:
We study the instability properties of Nesterov's ODE in non-conservative settings, where the driving term is not necessarily the gradient of a potential function. While convergence properties under Nesterov's ODE are well-characterized for optimization settings with gradient-based driving terms, we show that the presence of arbitrarily small non-conservative terms can lead to instability, a phenomenon previously observed empirically via numerical studies in optimization and game-theoretic problems. Our instability analysis combines multi-time scale techniques, such as averaging via variations-of-constants formula, and Floquet Theory, focusing on systems where the vector field is linear and its Helmholtz decomposition reveals a non-vanishing non-conservative component. To resolve the instability issue, the dynamics under non-vanishing non-conservative components, we study a regularization mechanism based on restarting. The resulting system is a hybrid dynamical system that mirrors Nesterov's ODE during intervals of flow, and implements resets of the momentum state through discrete periodic jumps. For this hybrid system, we establish novel explicit bounds on the resetting period that ensure the decrease of a suitable Lyapunov function, guaranteeing not only stability but also "accelerated" convergence rates under suitable smoothness and strong monotonicity properties on the driving term. Numerical simulations support our theoretical results.
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。