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

III: Small: Learning From Diverse Populations: A Complexity-Theoretic Perspective

III：小：向不同人群学习：复杂性理论的视角

基本信息

批准号：
1908774
负责人：
Omer Reingold
金额：
$ 50万
依托单位：
Stanford University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-10-01 至 2023-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1908774&HistoricalAwards=false
关键词：
III Small Learning Diverse Populations

项目摘要

Despite the successes of machine learning at complex prediction and classification tasks (such as which add a reader will click? or which word a speaker pronounced?), there is growing evidence that "state-of-the-art" predictors can perform significantly less accurately on minority populations than on the majority population. Indeed, a notable study of three commercial face recognition systems, known as the "Gender Shades" project demonstrated significant performance gaps across different subpopulations at natural classification tasks. Systematic errors on underrepresented subpopulations limit the overall utility of machine-learned prediction systems and may cause material harm to individuals from minority groups. To address accuracy disparity and systematic biases throughout machine learning, the project pursue a principled study of learning in the presence of diverse populations. The project puts high value on education, service to the research community, and wide dissemination of knowledge. The research activities will be accompanied by and integrated with curriculum development, research advising (for students at all levels), service, and outreach to other scientific communities and in popular writing. In addition, in the age of machine-learning and big data, the project's societal impact is twofold: making sure that algorithms work for everyone but also making sure algorithms uncover all potential talent, which exists in all communities.The project combines theoretical and empirical investigations to develop algorithmic tools for mitigating systematic bias across subpopulations and to answer basic scientific questions about why discrepancy in accuracy across subpopulations emerges in the first place. Specifically, the project aims to ask and resolve questions that arise in the context of learning from diverse populations along three main axes: (1) Improving predictions for underrepresented populations: Can learning algorithms be developed that provably do not overlook significant subpopulations, (2) Representing individuals to improve the ability to audit and repair models, (3) Understanding the causes for biases in machine common learning models and algorithms.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.

尽管机器学习在复杂的预测和分类任务上取得了成功（比如读者会点击哪个添加？或者说是一个说话者说的什么话？）越来越多的证据表明，“最先进的”预测器对少数群体的准确性可能远远低于对多数群体的准确性。事实上，一项针对三种商业人脸识别系统的著名研究（被称为“性别阴影”项目）表明，不同亚群在自然分类任务中存在显著的性能差距。代表性不足的亚群的系统性错误限制了机器学习预测系统的整体效用，并可能对少数群体的个人造成重大伤害。为了解决整个机器学习过程中的准确性差异和系统性偏差，该项目对存在不同人群的学习进行了原则性研究。该项目高度重视教育、为研究界服务和广泛传播知识。研究活动将伴随并与课程开发，研究咨询（为各级学生），服务和推广到其他科学界和流行的写作相结合。此外，在机器学习和大数据时代，该项目的社会影响是双重的：确保算法对每个人都有效，同时也确保算法发现所有潜在的人才，该项目结合了理论和实证调查，开发算法工具，以减轻亚群之间的系统性偏差，并回答有关为什么不同群体之间的准确性差异的基本科学问题。亚群首先出现。具体而言，该项目旨在提出和解决在向不同人群学习的背景下出现的问题，沿着三个主轴：（1）改善对代表性不足人群的预测：学习算法能否被开发出来，证明不会忽视重要的子群体，（2）代表个人，以提高审计和修复模型的能力，（3）了解机器常见学习模型和算法中偏见的原因。该奖项反映了NSF的法定使命，并且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（25）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models

高维广义线性模型的非渐近莫罗包络理论

DOI：
发表时间：
2022
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
Zhou, Lijia;Koehler, Frederic;Sur, Pragya;Sutherland, Danica J.;Srebro, Nathan
通讯作者：
Srebro, Nathan

Sample Amplification: Increasing Dataset Size even when Learning is Impossible, ICML

样本放大：即使无法学习，也可以增加数据集大小，ICML