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 2408.16656math.OC
收藏

非线性等式约束随机优化的两步长SQP方法

A Two Stepsize SQP Method for Nonlinear Equality Constrained Stochastic Optimization

University of North Carolina, Chapel Hill(北卡罗来纳大学教堂山分校)

Michael J. O'Neill

AI总结:

提出一种两步长SQP算法,通过分别缩放受方差影响的步长分量和整个步长,在约束违反和拉格朗日梯度范数上分别达到确定性SQP和随机SQP的最优复杂度。

摘要:

我们开发了一种序列二次优化(SQP)算法,用于最小化受确定性等式约束的随机目标函数。该方法利用两个不同的步长,一个专门缩放受随机梯度估计方差影响的步长分量,另一个缩放整个步长。我们证明,这种步长分裂方案在最坏情况下的复杂度结果优于该类问题已知的最佳结果。在近似满足约束违反方面,该复杂度结果与确定性SQP方法相匹配(相差常数因子),同时在近似最小化拉格朗日梯度范数方面匹配随机SQP方法的已知最优速率。我们还提出并分析了算法的多种变体。其中一种变体基于流行的无约束随机优化自适应梯度方法,另一种则结合了沿约束违反的受保护线搜索。初步数值实验显示,与最先进算法相比具有竞争力。此外,在这些实验中,我们观察到约束违反的收敛速度有所提高,正如理论结果所预测的那样。

英文摘要:

We develop a Sequential Quadratic Optimization (SQP) algorithm for minimizing a stochastic objective function subject to deterministic equality constraints. The method utilizes two different stepsizes, one which exclusively scales the component of the step corrupted by the variance of the stochastic gradient estimates and a second which scales the entire step. We prove that this stepsize splitting scheme has a worst-case complexity result which improves over the best known result for this class of problems. In terms of approximately satisfying the constraint violation, this complexity result matches that of deterministic SQP methods, up to constant factors, while matching the known optimal rate for stochastic SQP methods to approximately minimize the norm of the gradient of the Lagrangian. We also propose and analyze multiple variants of our algorithm. One of these variants is based upon popular adaptive gradient methods for unconstrained stochastic optimization while another incorporates a safeguarded line search along the constraint violation. Preliminary numerical experiments show competitive performance against state of the art algorithms. In addition, in these experiments, we observe an improved rate of convergence in terms of the constraint violation, as predicted by the 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。

↑