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 2603.09682math.OCcs.NAmath.NA
收藏

通过统一半定规划子问题的全局收敛三次牛顿法

A Globally Convergent Third-Order Newton Method via Unified Semidefinite Programming Subproblems

Massachusetts Institute of Technology(麻省理工学院);University of Oxford(牛津大学)

Yubo Cai, Wenqi Zhu, Coralia Cartis, Gioele Zardini

AI总结:

ALMTON通过统一半定规划子问题实现了无约束非凸优化的全局收敛三次牛顿法,具有更稳定的收敛性和更广的吸引盆地。

摘要:

我们提出了一种自适应Levenberg-Marquardt三次牛顿法(ALMTON),用于无约束非凸优化,提供了非正则化三次牛顿法的第一个全局收敛实现。不同于标准自适应正则化框架中的三次模型(AR3),该框架通过四次项来强制全局行为,ALMTON采用自适应Levenberg-Marquardt(二次)正则化。这种选择在每次迭代中保持三次模型,使得每个子问题都成为可解的半定规划(SDP)。特别是,ALMTON-Simple变体每次迭代只需求解一次SDP,使得每次迭代的成本均匀且可预测。算法上,ALMTON采用混合模式策略:当三次泰勒模型允许存在严格局部极小点且具有足够的曲率时,尝试无正则化三次步;只有在需要时才激活(或增加)二次正则化以确保模型良好定义且步长全局可靠。我们建立了全局收敛性,并证明了计算一个ε-近似一阶 stationary 点的最坏情况评估复杂度为O(ε^{-2})。数值实验表明,ALMTON相对于经典基线(梯度下降和阻尼牛顿)扩大了吸引盆地,并能在第二阶方法通常停滞的景观上取得进展。与最先进的三次实现(AR3-interp)相比,ALMTON收敛更一致且通常在更少的迭代中完成。我们还 characterized 了该方法的实际可扩展性限制,突显了随着维度增长,当前SDP求解器引入的计算瓶颈。

英文摘要:

We propose the Adaptive Levenberg-Marquardt Third-Order Newton Method (ALM-TON) method for unconstrained nonconvex optimization; to our knowledge, the framework provides the first globally convergent realization of the unregularized third-order Newton method. Unlike the standard Adaptive Regularization framework with third-order models (AR3), which enforces global behavior through a quartic term, ALMTON employs an adaptive Levenberg-Marquardt (quadratic) regularization. This choice preserves a cubic model at every iteration, so that every subproblem is a tractable semidefinite programming (SDP). Algorithmically, ALMTON follows a mixed-mode strategy: it attempts an unregularized thirdorder step whenever the cubic Taylor model admits a strict local minimizer with adequate curvature, and activates (or increases) quadratic regularization only when needed to ensure that the model is well posed and the step is globally reliable. For the Heuristic strategy, under the stated assumptions and an exact local-minimizer oracle, we prove finite termination at an $ε$-approximate first-order stationary point with $O\left(ε^{-2}\right)$ worst-case evaluation complexity. Moreover, if an accepted iterate enters the stated neighborhood of a positive-definite local minimizer, subsequent nonterminal steps recover the unregularized third-order Newton recursion and its cubic local rate. Under a common post hoc terminal audit over 4,500 deterministic starts on five two-dimensional nonconvex problems, both ALMTON variants satisfy the terminal criterion on $99.91 \%$ of the instances, compared with $55.42 \%$ for the unregularized third-order Newton method. This robustness gain comes at substantial SDP cost: AR$2$ is faster, so the results support robust globalization of the unregularized cubic model rather than overall empirical superiority.

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。

↑