权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

AF: Medium: Collaborative Research: Foundations of Fair Data Analysis

AF：媒介：协作研究：公平数据分析的基础

基本信息

批准号：
1763307
负责人：
AARON ROTH
金额：
$ 95万
依托单位：
University of Pennsylvania
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2018
资助国家：
美国
起止时间：
2018-07-01 至 2024-06-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1763307&HistoricalAwards=false
关键词：
AF Medium Collaborative Research Foundations

项目摘要

Machine learning algorithms increasingly make or inform critical decisions that affect peoples' every day lives. For instance, algorithms make decisions pertaining to hiring, college admissions, credit card and mortgage approvals, sentencing and parole of the incarcerated, first-responder deployment, and what advertisements and search results a user sees on the internet. An attractive feature is that these algorithms can efficiently process large amounts of data in making these decisions, thus hopefully improving economic and social efficiency. Because such decisions are so consequential, their fairness has become a matter of increasing concern. It has been argued that automation, by removing the human element, guarantees fairness, but this is not so -- several empirical studies have demonstrated that automation is no panacea. Further, the reasons for unfairness and discrimination can be complex and non-obvious. This project will study the frictions that may cause unfairness in algorithmic decision making, and the costs of mitigating unfairness -- that is, quantitative trade-offs between fairness and other desiderata, including accuracy, computational efficiency, and economic efficiency.Specifically, this project will study frictions to fairness arising from several factors. There may not be sufficient data about minority populations. There can be feedback loops arising from the fact that observations can only be made on an individual if a risky action is taken, e.g., the person is granted a loan, or hired. Decision makers can be myopic, choosing to maximize short-term gains rather than exploring riskier options that may pay off in the long run. Economic frictions include self-confirming equilibria---differing subjective perceptions of opportunities leading to choices by individuals and communities which sustain those perceptions, and competition among classifiers (for example, credit agencies) leading to less accurate qualifiers in equilibrium. Finally, the problem of finding fair and accurate classifiers can be computationally intractable. This project will seek ways to mitigate the unfairness arising from these frictions. It will study the cost of incentivizing myopic agents to explore and examine the short-term costs of such incentives, and their long-term impact on fairness. It will also seek to design computationally tractable classifiers that achieve provably good approximations for fairness and accuracy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

机器学习算法越来越多地做出或告知影响人们日常生活的关键决策。例如，算法可以做出与招聘、大学录取、信用卡和抵押贷款审批、监禁人员的判刑和假释、第一反应部署以及用户在互联网上看到的广告和搜索结果有关的决定。一个吸引人的特点是，这些算法可以有效地处理大量的数据，在这些决策，从而有望提高经济和社会效率。由于这些决定是如此重要，其公平性已成为一个日益关注的问题。有人认为，自动化通过消除人为因素，保证了公平，但事实并非如此-一些实证研究表明，自动化不是万能药。此外，不公平和歧视的原因可能是复杂和不明显的。本项目将研究在算法决策中可能导致不公平的摩擦，以及减轻不公平的成本，即公平与其他必要条件（包括准确性、计算效率和经济效率）之间的定量权衡。具体来说，本项目将研究由几个因素引起的公平摩擦。关于少数群体的数据可能不足。可能存在反馈回路，这是因为只有在采取危险行动的情况下才能对个体进行观察，例如，该人获得贷款或被雇用。决策者可能是短视的，选择最大化短期收益，而不是探索可能在长期内获得回报的风险更高的选择。经济摩擦包括自我确认的均衡-对机会的不同主观看法导致个人和社区做出维持这些看法的选择，以及分类器（例如，信贷机构）之间的竞争导致均衡中不太准确的限定符。最后，找到公平和准确的分类器的问题可能是计算上难以解决的。该项目将寻求减轻这些摩擦所产生的不公平的方法。它将研究激励短视代理人的成本，以探索和研究这种激励的短期成本，以及它们对公平的长期影响。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（21）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

An Algorithmic Framework for Fairness Elicitation

DOI：
10.4230/lipics.forc.2021.2
发表时间：
2020-10
期刊：
影响因子：
0
作者：
Christopher Jung;Michael Kearns;Seth Neel;Aaron Roth;Logan Stapleton;Zhiwei Steven Wu
通讯作者：
Christopher Jung;Michael Kearns;Seth Neel;Aaron Roth;Logan Stapleton;Zhiwei Steven Wu

Practical Adversarial Multivalid Conformal Prediction

DOI：
10.48550/arxiv.2206.01067
发表时间：
2022-06
期刊：
ArXiv
影响因子：
0
作者：
O. Bastani;Varun Gupta;Christopher Jung;Georgy Noarov;Ramya Ramalingam;Aaron Roth
通讯作者：
O. Bastani;Varun Gupta;Christopher Jung;Georgy Noarov;Ramya Ramalingam;Aaron Roth

Online Minimax Multiobjective Optimization: Multicalibeating and Other Applications

在线极小极大多目标优化：多校准和其他应用