CAREER: Towards a theory of machine learning with strategic interactions

职业：走向具有战略互动的机器学习理论

• 批准号: 2145898
• 负责人: Nika Haghtalab
• 金额: $ 60万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2027-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2145898&HistoricalAwards=false
• 关键词: CAREER; Towards; theory; machine; learning

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Machine learning (ML) algorithms use observed sampled data to uncover general patterns that can then be used for making predictions. Learning systems that interact with human data and stakeholders (such as those used in personalized medicine, content curation, financial markets, hiring, and lending) take place in a complex social and economic context. In this wide range of applications, there are feedback loops between learning algorithms and people that impact the quality of the learning process and the wellbeing of people. These feedback loops are currently not captured by the classical theory of ML, and handling them in an ad hoc, non-mathematical, way could have major social repercussions. This project will develop a rigorous mathematical framework for addressing interactions between learning systems and people and will draw from a wide range of academic traditions and fields, including Theory of Computing, Artificial Intelligence, Economics and Computation. This project also addresses educational and community building plans for enabling the next generations of students to contribute to a theory of machine learning for emerging and modern needs through cross-disciplinary research.This project will build a theoretical foundation for ensuring both the performance of learning algorithms in the presence of everyday social and economic forces and the integrity of social and economic forces that are born out of the use of machine-learning systems. To achieve this, the investigator will consider adversarial, strategic, and collaborative interactions. For adversarial and long-term strategic interactions, the project will explore online decision processes and contribute online learning algorithms that perform well in presence of more realistic adaptive and non-myopic strategic agents. The project also explores the long-term social impact of strategic play and communication on learning and quality of available information, with an eye towards understanding and addressing biased and polarized beliefs. Additionally, to reap the full benefit of collaborative interactions, the project will align the performance of learning algorithms with the needs and preferences of participating agents. This will lead to the design of collaborative learning protocols that are differentially private, statistically efficient, and equitable. This project also includes outreach, mentoring, and educational plans that will complement its technical goals, including a workshop series on "Learning in presence of Strategic Behavior" that brings together members of different communities and helps set an agenda for the field and "Learning Theory Alliance" that is a large-scale mentoring initiative for supporting the machine learning theory community.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.

该奖项的全部或部分资金来源于《2021 年美国救援计划法案》（公法 117-2）。机器学习 (ML) 算法使用观察到的采样数据来揭示一般模式，然后将其用于进行预测。与人类数据和利益相关者（例如个性化医疗、内容管理、金融市场、招聘和贷款中使用的系统）交互的学习系统发生在复杂的社会和经济背景下。在如此广泛的应用中，学习算法和人之间存在反馈循环，影响学习过程的质量和人们的福祉。这些反馈循环目前尚未被 ML 的经典理论所捕获，以临时的、非数学的方式处理它们可能会产生重大的社会影响。该项目将开发一个严格的数学框架来解决学习系统与人之间的相互作用，并将借鉴广泛的学术传统和领域，包括计算理论、人工智能、经济学和计算。该项目还涉及教育和社区建设计划，使下一代学生能够通过跨学科研究为满足新兴和现代需求的机器学习理论做出贡献。该项目将为确保学习算法在日常社会和经济力量存在下的性能以及因使用机器学习系统而产生的社会和经济力量的完整性奠定理论基础。为了实现这一目标，研究者将考虑对抗性、战略性和协作性互动。对于对抗性和长期战略互动，该项目将探索在线决策过程，并贡献在线学习算法，这些算法在更现实的自适应和非短视战略代理的存在下表现良好。该项目还探讨了战略游戏和沟通对学习和可用信息质量的长期社会影响，着眼于理解和解决偏见和两极分化的信念。此外，为了充分发挥协作交互的优势，该项目将使学习算法的性能与参与代理的需求和偏好保持一致。这将导致协作学习协议的设计具有差异化隐私性、统计效率和公平性。该项目还包括与其技术目标相辅相成的外展、指导和教育计划，包括“战略行为中的学习”系列研讨会，该研讨会汇集了不同社区的成员，帮助制定该领域的议程，以及“学习理论联盟”，这是一项支持机器学习理论社区的大规模指导计划。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力评估进行评估，认为值得支持。 优点和更广泛的影响审查标准。

项目成果

Oracle-Efficient Online Learning for Smoothed Adversaries

Oracle 高效在线学习，轻松应对对手

• 发表时间: 2022
• 期刊: Advances in Neural Information Processing Systems (NeurIPS 2022
• 作者: Haghtalab, Nika;Han, Yanjun;Shetty, Abhishek;Yang, Kunhe
• 通讯作者: Yang, Kunhe

Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty

利用评论：学习在买家和卖家的不确定性下定价

• DOI: 10.1145/3580507.3597663
• 发表时间: 2023
• 期刊: ACM
• 作者: Guo, Wenshuo;Haghtalab, Nika;Kandasamy, Kirthevasan;Vitercik, Ellen
• 通讯作者: Vitercik, Ellen

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

多重校准的统一视角：多目标学习的游戏动力学

• 发表时间: 2023
• 期刊: Advances in Neural Information Processing Systems 36 (NeurIPS 2023
• 作者: Haghtalab, Nika;Jordan, Michael;Zhao, Eric
• 通讯作者: Zhao, Eric

Smoothed Analysis of Sequential Probability Assignment

顺序概率分配的平滑分析

• 发表时间: 2023
• 期刊: Advances in Neural Information Processing Systems 36 (NeurIPS 2023
• 作者: Bhatt, Alankrita;Haghtalab, Nika;Shetty, Abhishek
• 通讯作者: Shetty, Abhishek

Learning in Stackelberg Games with Non-myopic Agents

与非近视智能体一起在 Stackelberg 游戏中学习

• DOI: 10.1145/3490486.3538308
• 发表时间: 2022
• 期刊: Proceedings of the 23rd ACM Conference on Economics and Computation
• 作者: Haghtalab, Nika;Lykouris, Thodoris;Nietert, Sloan;Wei, Alexander
• 通讯作者: Wei, Alexander