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 1301.2663cs.GT
收藏

可接近性、后悔和校准;含义和等价性

Approachability, Regret and Calibration; implications and equivalences

Vianney Perchet

摘要:

Blackwell可接近性、后悔最小化和校准是评价不同序贯决策问题或参与者与自然之间重复博弈中策略(或算法)的三个标准。虽然乍一看它们没有任何共同之处,但它们之间的联系已经被发现:在一些辅助博弈中,通过遵循可接近性策略,可以构建一致的和校准的策略。我们收集了著名的或最近的结果,并提供新的,以发展和推广Blackwell的优雅的理论。最后的目标是展示它如何可以被用来作为一个基本的强大的工具来展示一类新的直观的算法,基于简单的几何性质。为了完整,我们还证明了可接近性可以被视为一致或校准策略存在的副产品。

英文摘要:

Blackwell approachability, regret minimization and calibration are three criteria evaluating a strategy (or an algorithm) in different sequential decision problems, or repeated games between a player and Nature. Although they have at first sight nothing in common, links between have been discovered: both consistent and calibrated strategies can be constructed by following, in some auxiliary game, an approachability strategy. We gathered famous or recent results and provide new ones in order to develop and generalize Blackwell's elegant theory. The final goal is to show how it can be used as a basic powerful tool to exhibit a new class of intuitive algorithms, based on simple geometric properties. In order to be complete, we also prove that approachability can be seen as a byproduct of the very existence of consistent or calibrated strategies.

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。

↑