Artificial Intelligence ( IF 14.4 ) Pub Date : 2023-12-07 , DOI: 10.1016/j.artint.2023.104049 Masoud Seddighin , Saeed Seddighin
In this work, we study the maximin share fairness notion () for allocation of indivisible goods in the subadditive and fractionally subadditive settings. While previous work refutes the possibility of obtaining an allocation which is better than 1/2-MMS, the only positive result for the subadditive setting states that when the number of items is equal to m, there always exists an -MMS allocation. Since the number of items may be larger than the number of agents (n), such a bound can only imply a weak bound of - allocation in general.
In this work, we improve this bound exponentially to -MMS guarantee. In addition to this, we prove that when the valuation functions are fractionally subadditive, a 0.2192235-MMS allocation is guaranteed to exist. This also improves upon the previous bound of 1/5-MMS guarantee for the fractionally subadditive setting.
中文翻译:
改进次加法和分数次加法公平分配问题的最大最小保证
在这项工作中,我们研究了最大最小份额公平概念() 用于在次加法和部分次加法设置中分配不可分割的商品。虽然以前的工作驳斥了获得优于 1/2-MMS 的分配的可能性,但次加性设置的唯一积极结果表明,当项目数等于 m,总是存在 -彩信分配。由于项目的数量可能大于代理的数量(n),因此这样的界限只能暗示的弱界限-分配一般。
在这项工作中,我们将这个界限以指数方式改进为-彩信保证。除此之外,我们还证明,当估值函数部分可加时,保证存在 0.2192235-MMS 分配。这也改进了之前分数次加性设置的 1/5-MMS 保证界限。