arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2307.03335math.OC
收藏

用于约束优化的随机子空间梯度方法

Randomized subspace gradient method for constrained optimization

Ryota Nozawa, Pierre-Louis Poirion, Akiko Takeda

AI总结:

本文提出将梯度投影到活动约束梯度张成子空间的随机投影上的随机子空间梯度方法,用于高维约束优化,理论证明其可比确定性版本采用更大步长,并在梯度难以直接获取时具有时间复杂度优势。

摘要:

我们针对高维约束优化问题提出随机子空间梯度方法。虽然已有针对无约束优化问题的类似研究,但由于处理约束的困难,针对约束优化问题的研究很少。我们的算法将梯度向量投影到一个子空间上,该子空间是由活动约束的梯度所张成子空间的随机投影。我们在线性和非线性设置下确定了最坏情况迭代复杂度,并从理论上证实我们的算法可以比其确定性版本采用更大的步长。由于能够采用更长步长以及随机子空间梯度的优势,我们表明当梯度难以获得时,我们的算法在时间复杂度方面尤其高效。数值实验表明,由于子空间选择的随机性,它们往往能找到更好的解。此外,在梯度无法直接获得而需要通过方向导数来获取梯度的情况下,它们也表现良好。

英文摘要:

We propose randomized subspace gradient methods for high-dimensional constrained optimization. While there have been similarly purposed studies on unconstrained optimization problems, there have been few on constrained optimization problems due to the difficulty of handling constraints. Our algorithms project gradient vectors onto a subspace that is a random projection of the subspace spanned by the gradients of active constraints. We determine the worst-case iteration complexity under linear and nonlinear settings and theoretically confirm that our algorithms can take a larger step size than their deterministic version. From the advantages of taking longer step and randomized subspace gradients, we show that our algorithms are especially efficient in view of time complexity when gradients cannot be obtained easily. Numerical experiments show that they tend to find better solutions because of the randomness of their subspace selection. Furthermore, they performs well in cases where gradients could not be obtained directly, and instead, gradients are obtained using directional derivatives.

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。

↑