“I'd recommend the articles for a better explanation.”
Inherent Trade-Offs in the Fair Determination of Risk Scores
证明多种公平性条件除极特殊情形外无法同时满足
针对公众对算法分类中「对不同群体公平」含义的争论,作者形式化了处于争论核心的三种公平性条件,并证明除了高度受限的特殊情形外,没有任何方法能同时满足这三个条件。进一步地,即使只是近似同时满足,也要求数据近似落在定理所确定的某个受限特殊情形里。这表明关键的公平概念彼此不相容,并为权衡它们提供了思考框架。
HN 上的人用它说明各种「公平」定义在群体基准率不同时无法同时满足(如校准与群体间平衡),是讨论算法歧视时常引用的不可能性结果。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“I recommend _The impossibility of “fairness”: a generalized impossibility result for decisions_[0] and _Inherent Trade-Offs in the Fair Determination of Risk Scores_[1]”
“The conclusion there is simply a theorem: it's mathematically impossible to be both well calibrated”
“It turns out there is a beautiful mathematical result that shows that the different definitions of "fairness" are inherently incompatible with each other and cannot be satisfied at the same time.”
“there are impossibility theorems that say you can't meet everyone's definition of "nondiscriminatory" except in a few trivial cases.”
“We actually have a mathematical proof (which is quite simple) why this is impossible.”
看全部 8 条 →
“Of course, defining "racism" itself gets extremely tricky because many definitions of racism are mutually contradictory.”
“that cannot possibly be fulfilled at the same time if there is any difference between the groups.”
- Inherent Trade-Offs in the Fair Determination of Risk Scores ↗nabla9 · 2017-09-24 · 2 分