CAREER: A Sequential Learning Framework with Applications to Learning from Crowds

职业：顺序学习框架及其在群体学习中的应用

• 批准号: 1845444
• 负责人: Xi Chen
• 金额: $ 49.78万
• 依托单位: New York 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: 2019-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1845444&HistoricalAwards=false
• 关键词: CAREER; Sequential; Learning; Framework; Applications

While traditional machine learning usually deals with given static data, many online data are collected via a sequence of interactions with agents such as crowd labelers or customers. The motivating applications of the project include crowd labeling tasks (which is a powerful paradigm for utilizing human wisdom to collect data labels), sequential product recommendation, and online multi-product pricing. For all these applications, online learning and sequential decision-making are indispensable to each other. The objective of this project is to develop new sequential learning algorithms with rigorous theoretical guarantees. The developed framework will not only make fundamental technical contributions but also facilitate many important applications. For example, it will greatly improve the aggregated answers from crowd labelers with a significantly reduced cost. It can enhance the revenue of business while improving the customers' satisfaction by providing accurate recommendations. In addition, this project also facilitates the development of new courses on machine learning for business school students, which helps bring the knowledge from data science to future business leaders, and provides training to K-12 students, with an emphasis on those from underrepresented groups.This project strives to develop a unified learning and decision-making framework, which serves as an intellectual bridge connecting machine learning, stochastic optimization, and decision theory. In particular, there are three complementary research thrusts. The first thrust creates a suite of efficient algorithms that deal with complex task structures, such as ranking with transitivity structures or product recommendation with combinatorial structures, in a non-stationary environment. The algorithms will extend the bandit learning with finite independent arms into the setting with a complex correlation structure among potentially infinite number of arms. The second thrust seeks a cost-effective paradigm that either incorporates "optimal stopping" rule under a certain budget constraint or minimizes the sample complexity. The third thrust systematically evaluates the algorithms and theories on real problems coming from both crowdsourcing and other business-related applications. Moreover, since the computational efficiency and scalability is an important focus, the project will also advance the distributed statistical learning and stochastic optimization fields.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.

虽然传统的机器学习通常处理给定的静态数据，但许多在线数据是通过与代理（如人群标签或客户）的一系列交互收集的。该项目的激励应用包括人群标签任务（这是利用人类智慧收集数据标签的强大范例），顺序产品推荐和在线多产品定价。对于所有这些应用，在线学习和顺序决策是不可或缺的。该项目的目标是开发新的序列学习算法，具有严格的理论保证。所开发的框架不仅将做出基本的技术贡献，而且还将促进许多重要的应用。例如，它将极大地改善来自人群标签器的聚合答案，同时显著降低成本。它可以通过提供准确的建议来提高业务收入，同时提高客户的满意度。此外，该项目还为商学院学生开发了新的机器学习课程，有助于将数据科学的知识带给未来的商业领袖，并为K-12学生提供培训，重点是那些来自代表性不足的群体。该项目致力于开发一个统一的学习和决策框架，作为连接机器学习，随机优化和决策理论。特别是，有三个互补的研究重点。第一个推力创建了一套有效的算法，处理复杂的任务结构，如排名与传递性结构或产品推荐与组合结构，在一个非平稳的环境。该算法将具有有限独立臂的强盗学习扩展到具有潜在无限多个臂之间的复杂相关结构的设置。第二个推力寻求一个具有成本效益的范式，无论是采用“最佳停止”规则下，一定的预算约束或最小化样本的复杂性。第三个重点是系统地评估来自众包和其他商业相关应用的真实的问题的算法和理论。此外，由于计算效率和可扩展性是一个重要的焦点，该项目还将推进分布式统计学习和随机优化领域。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

Robust Dynamic Assortment Optimization in the Presence of Outlier Customers

存在异常客户时的稳健动态分类优化

• DOI: 10.1287/opre.2020.0281
• 发表时间: 2023
• 期刊: Operations Research
• 影响因子: 2.7
• 作者: Chen, Xi;Krishnamurthy, Akshay;Wang, Yining
• 通讯作者: Wang, Yining

Differential Privacy in Personalized Pricing with Nonparametric Demand Models

非参数需求模型个性化定价中的差异隐私

• DOI: 10.1287/opre.2022.2347
• 发表时间: 2022
• 期刊: Operations Research
• 影响因子: 2.7
• 作者: Chen, Xi;Miao, Sentao;Wang, Yining
• 通讯作者: Wang, Yining

Robust Dynamic Pricing with Demand Learning in the Presence of Outlier Customers

在存在异常客户的情况下通过需求学习进行稳健的动态定价

• DOI: 10.1287/opre.2022.2280
• 发表时间: 2022
• 期刊: Operations Research
• 影响因子: 2.7
• 作者: Chen, Xi;Wang, Yining
• 通讯作者: Wang, Yining

Bayesian Decision Process for Budget-efficient Crowdsourced Clustering

• DOI: 10.24963/ijcai.2020/283
• 发表时间: 2020-07

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

无限武装线性上下文强盗的严格遗憾界限

• 发表时间: 2021
• 期刊: Proceedings of The 24th International Conference on Artificial Intelligence and Statistics
• 作者: Li, Yingkai;Wang, Yining;Chen, Xi;Zhou, Yuan
• 通讯作者: Zhou, Yuan