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 2403.10063cs.LGcs.AIcs.CCmath.OC
收藏

对抗性DR-次模优化的统一无投影算法

Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization

Purdue University(普渡大学);Iowa State University(爱荷华州立大学)

Mohammad Pedramfar, Yididiya Y. Nadew, Christopher J. Quinn, Vaneet Aggarwal

AI总结:

本文提出统一的Frank-Wolfe型无投影算法用于对抗性连续DR-次模优化,覆盖全信息与(半)赌博机反馈、单调与非单调函数及多种约束,在非单调设置中首次获得次线性α-遗憾界,在单调设置8个案例中7个达到最优水平。

摘要:

本文介绍了用于对抗性连续DR-次模优化的统一无投影Frank-Wolfe类型算法,涵盖全信息和(半)赌博机反馈、单调和非单调函数、不同约束以及随机查询类型等场景。对于非单调设置中考虑的每个问题,所提出的算法要么是首个具有已证明的次线性α-遗憾界的算法,要么比现有最优方法具有更好的α-遗憾界,其中α是离线设置中相应的近似界。在单调设置中,所提出的方法在8个考虑案例中的7个中,在无投影算法中给出了最先进的次线性α-遗憾界,同时在剩余案例中匹配了现有结果。此外,本文还研究了对抗性DR-次模优化的半赌博机和赌博机反馈,推进了对该优化领域的理解。

英文摘要:

This paper introduces unified projection-free Frank-Wolfe type algorithms for adversarial continuous DR-submodular optimization, spanning scenarios such as full information and (semi-)bandit feedback, monotone and non-monotone functions, different constraints, and types of stochastic queries. For every problem considered in the non-monotone setting, the proposed algorithms are either the first with proven sub-linear $α$-regret bounds or have better $α$-regret bounds than the state of the art, where $α$ is a corresponding approximation bound in the offline setting. In the monotone setting, the proposed approach gives state-of-the-art sub-linear $α$-regret bounds among projection-free algorithms in 7 of the 8 considered cases while matching the result of the remaining case. Additionally, this paper addresses semi-bandit and bandit feedback for adversarial DR-submodular optimization, advancing the understanding of this optimization area.

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。

↑