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 1802.02246math.OC
收藏

二层规划的逼近方法

Approximation Methods for Bilevel Programming

Saeed Ghadimi, Mengdi Wang

摘要:

研究了一类内目标函数为强凸的双层规划问题。在内外目标函数的偏导数都满足一定的mile假设条件下,给出了求解这类问题的一个近似算法,并在不同的外目标函数凸性假设条件下给出了算法的有限时间收敛性分析.我们还提出了一个加速变形的这种方法,提高了收敛速率下凸性假设。此外,我们推广了我们的结果在随机设置下,只有噪音信息的两个目标函数。据我们所知,这是第一次,这样的(随机)近似算法建立迭代复杂性(样本复杂性)提供了双层规划。

英文摘要:

In this paper, we study a class of bilevel programming problem where the inner objective function is strongly convex. More specifically, under some mile assumptions on the partial derivatives of both inner and outer objective functions, we present an approximation algorithm for solving this class of problem and provide its finite-time convergence analysis under different convexity assumption on the outer objective function. We also present an accelerated variant of this method which improves the rate of convergence under convexity assumption. Furthermore, we generalize our results under stochastic setting where only noisy information of both objective functions is available. To the best of our knowledge, this is the first time that such (stochastic) approximation algorithms with established iteration complexity (sample complexity) are provided for bilevel programming.

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。

↑