AF: Small: Learning and Optimization with Strategic Data Sources

AF：小型：利用战略数据源进行学习和优化

• 批准号: 1718549
• 负责人: Yiling Chen
• 金额: $ 45万
• 依托单位: Harvard University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2021-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1718549&HistoricalAwards=false
• 关键词: AF; Small; Learning; Optimization; Strategic

The goal of this research project is to develop new results in machine learning and optimization when training data for machine learning or information about optimization problems is acquired from strategic sources. We are blessed with unprecedented abilities to connect with people all over the world: buying and selling products, sharing information and experiences, asking and answering questions, collaborating on projects, borrowing and lending money, and exchanging excess resources. These activities result in rich data that scientists can use to understand human social behavior, generate accurate predictions, find cures for diseases, and make policy recommendations. Machine learning and optimization traditionally take such data as given, for example treating them as independent samples drawn from some unknown probability distribution. However, such data are possessed or generated by people in the context of specific rules of interaction. Hence, what data become available and the quality of available data are results of strategic decisions. For example, people with sensitive medical conditions may be less willing to reveal their medical data in a survey and freelance workers may not put in a good-faith effort in completing a task. This strategic aspect of data challenges fundamental assumptions in machine learning and optimization. The research project takes a holistic view that jointly considers data acquisition with learning and optimization. It will bring improved benefits in business, government, and societal decision-making processes where machine learning and optimization are widely applicable. The research project also involves the mentoring of PhD students, innovation in graduate teaching, and engagement of members of underrepresented groups in research.The PI will pursue a broad research agenda developing a fundamental understanding of how acquiring data from strategic sources affects the objectives of machine learning and optimization. The first set of goals aims to develop a theory for machine learning when a learning algorithm needs to purchase data from data holders who cannot fabricate their data but each have a private cost associated with revealing their data. A notion of economic efficiency for machine learning will be established. The second set of goals will further advance the frontier of machine learning by designing joint elicitation and learning mechanisms when data are acquired from strategic agents but the quality of the contributed data cannot be directly verified. The third set of goals will develop optimization algorithms with good theoretical guarantees when parameters of an optimization problem may be unknown initially but the algorithm designer can gather information about the parameters from strategic agents.

该研究项目的目标是在从战略来源获得机器学习的训练数据或有关优化问题的信息时，开发机器学习和优化的新成果。 我们有幸拥有前所未有的能力与世界各地的人们联系：购买和销售产品，分享信息和经验，提出和回答问题，合作项目，借贷资金，以及交换多余的资源。 这些活动产生了丰富的数据，科学家可以利用这些数据来了解人类的社会行为，做出准确的预测，找到疾病的治疗方法，并提出政策建议。 机器学习和优化传统上将这些数据视为给定的，例如将它们视为从某些未知概率分布中提取的独立样本。 然而，这些数据是由人们在特定的互动规则背景下拥有或产生的。 因此，什么样的数据可以获得以及可用数据的质量是战略决策的结果。 例如，患有敏感疾病的人可能不太愿意在调查中透露他们的医疗数据，自由职业者可能不会真诚地努力完成任务。 数据的这一战略方面挑战了机器学习和优化中的基本假设。 该研究项目采取整体观点，将数据采集与学习和优化结合起来考虑。 它将为机器学习和优化广泛应用的商业、政府和社会决策过程带来更大的好处。 该研究项目还涉及博士生的指导，研究生教学的创新，以及研究中代表性不足的群体成员的参与。PI将追求广泛的研究议程，发展从战略来源获取数据如何影响机器学习和优化目标的基本理解。 第一组目标旨在开发一种机器学习理论，当学习算法需要从数据持有者那里购买数据时，这些数据持有者不能伪造他们的数据，但每个人都有与披露他们的数据相关的私人成本。 将建立机器学习的经济效率概念。 第二组目标将通过设计联合启发和学习机制，进一步推进机器学习的前沿，当数据是从战略代理获得的，但贡献的数据的质量不能直接验证。 第三组目标将开发具有良好理论保证的优化算法，当优化问题的参数最初可能是未知的，但算法设计者可以从战略代理收集有关参数的信息。

项目成果

Optimal Advertising for Information Products

信息产品优化广告

• DOI: 10.1145/3465456.3467649
• 发表时间: 2021
• 期刊: Proceedings of the 22nd ACM Conference on Economics and Computation (EC 2021
• 作者: Zheng, Shuran;Chen, Yiling
• 通讯作者: Chen, Yiling

Learning Strategy-Aware Linear Classifiers

学习策略感知线性分类器

• 发表时间: 2020
• 期刊: Proc. of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020
• 作者: Chen, Yiling;Liu, Yang;Podimata, Chara
• 通讯作者: Podimata, Chara

Truthful Data Acquisition via Peer Prediction

通过同行预测获取真实数据

• 发表时间: 2020
• 期刊: Proc. of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020
• 作者: Chen, Yiling;Shen, Yiheng;Zheng, Shuran.
• 通讯作者: Zheng, Shuran.

Active Information Acquisition for Linear Optimization

• 发表时间: 2017-09
• 期刊: ArXiv
• 作者: Shuran Zheng;Bo Waggoner;Yang Liu;Yiling Chen

Forecast Aggregation via Peer Prediction

通过同行预测进行预测聚合

• 发表时间: 2021
• 期刊: Proceedings of the Ninth AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2021
• 作者: Wang, Juntao;Liu, Yang;Chen, Yiling
• 通讯作者: Chen, Yiling