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 2304.14907math.OCcs.LG
收藏

一种基于随机梯度的内点算法用于求解光滑有界约束优化问题

A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems

Lehigh University(利哈伊大学);Czech Technical University(捷克技术大学)

Frank E. Curtis, Vyacheslav Kungurtsev, Daniel P. Robinson, Qi Wang

AI总结:

提出一种基于随机梯度的内点算法,用于求解光滑有界约束优化问题,在确定性和随机性设置下均满足收敛保证,并实验证明优于投影法。

摘要:

本文提出、分析并实验验证了一种基于随机梯度的内点算法,用于在界约束下最小化连续可微(可能非凸)的目标函数。该算法与其他求解光滑非凸优化问题的内点方法不同,因为其搜索方向使用随机梯度估计计算。它还独特地使用了可行区域的内邻域——由正且趋于零的邻域参数序列定义——迭代点被强制保持在该邻域内。研究表明,通过仔细平衡障碍、步长和邻域序列,所提出的算法在确定性和随机性设置下均满足收敛保证。数值实验结果表明,在两种设置下,该算法都能优于基于投影的方法。

英文摘要:

A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function (that may be nonconvex) subject to bound constraints is presented, analyzed, and demonstrated through experimental results. The algorithm is unique from other interior-point methods for solving smooth nonconvex optimization problems since the search directions are computed using stochastic gradient estimates. It is also unique in its use of inner neighborhoods of the feasible region -- defined by a positive and vanishing neighborhood-parameter sequence -- in which the iterates are forced to remain. It is shown that with a careful balance between the barrier, step-size, and neighborhood sequences, the proposed algorithm satisfies convergence guarantees in both deterministic and stochastic settings. The results of numerical experiments show that in both settings the algorithm can outperform projection-based methods.

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。

↑