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 2107.05040math.OC
收藏

对Nesterov加速法变分解释的再思考

Rethinking the Variational Interpretation of Nesterov's Accelerated Method

Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand

摘要:

Nesterov动量的连续时间模型为理解凸优化中加速现象的本质提供了一个发人深省的视角。这一研究领域的主要思想之一来自经典力学领域,并提出将Nesterov的轨迹与一组相对于所谓的Bregman Lagrangian的Euler-Lagrange方程的解联系起来。近年来,这种方法导致了许多新的(随机)加速算法的发现,并为结构保持加速方法的设计提供了坚实的理论基础。在这项工作中,我们重新审视这一想法,并提供了一个深入的分析,从变分法的角度来看,相对于布雷格曼拉格朗日的行动。我们的主要发现是,虽然Nesterov的方法是一个固定点的行动,它往往不是一个极小,而是一个鞍点,这个功能在空间中的可微曲线。这一发现挑战了Nesterov方法变分解释背后的主要直觉,并为加速路径的有趣几何提供了额外的见解。

英文摘要:

The continuous-time model of Nesterov's momentum provides a thought-provoking perspective for understanding the nature of the acceleration phenomenon in convex optimization. One of the main ideas in this line of research comes from the field of classical mechanics and proposes to link Nesterov's trajectory to the solution of a set of Euler-Lagrange equations relative to the so-called Bregman Lagrangian. In the last years, this approach led to the discovery of many new (stochastic) accelerated algorithms and provided a solid theoretical foundation for the design of structure-preserving accelerated methods. In this work, we revisit this idea and provide an in-depth analysis of the action relative to the Bregman Lagrangian from the point of view of calculus of variations. Our main finding is that, while Nesterov's method is a stationary point for the action, it is often not a minimizer but instead a saddle point for this functional in the space of differentiable curves. This finding challenges the main intuition behind the variational interpretation of Nesterov's method and provides additional insights into the intriguing geometry of accelerated paths.

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。

↑