AF: Small: New Directions in Learning Theory

AF：小：学习理论的新方向

• 批准号: 1800317
• 负责人: Avrim Blum
• 金额: $ 9.8万
• 依托单位: Toyota Technological Institute at Chicago
• 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: 2017-08-01 至 2019-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1800317&HistoricalAwards=false
• 关键词: AF; Small; New; Directions; Learning

This project is to develop core principles and technologies for systems that learn from observation and experience in order to better help their users. While there is already a significant body of work in the area of machine learning, today's interconnected world provides both new challenges and new opportunities that classic methods are not able to address or take advantage of. This project has three main thrusts. The first involves development of methods that can extract useful information from auxiliary sources in addition to traditional labeled data. This includes methods for quickly learning multiple related tasks by taking advantage of ways in which they relate to each other. The second involves approaches for learning about what different users or agents want by observing the results of their interactions. Finally, the third thrust involves development of new rigorous methods for quickly estimating the amount of resources that would be needed to solve a given learning task. Broader impacts of the project include the training of a diverse set of graduate students, improving undergraduate curricula with respect to machine learning technology, and developing a new book for advanced undergraduates on algorithms and analysis for data science.More specifically, the first main thrust of this work involves a combination of unsupervised, semi-supervised, and multi-task learning. This work will investigate problems of estimating error rates from unlabeled data, unifying co-training and topic models, learning multiple related tasks from limited supervision, and learning new representations of data using tools from high-dimensional geometry. The second main thrust will focus on reconstructing estimates of agent utilities from observing the outcomes of economic mechanisms such as combinatorial auctions. This thrust also includes problems of learning the rules of unknown mechanisms from experimentation. Finally, the last thrust focuses on development of the theory of property testing for machine learning problems, with the goal of quickly estimating natural formal measures of complexity of a given learning task.

该项目旨在为从观察和经验中学习的系统开发核心原则和技术，以便更好地帮助用户。 虽然在机器学习领域已经有了大量的工作，但当今互联的世界提供了经典方法无法解决或利用的新挑战和新机遇。 该项目有三个主要目标。 第一个涉及的方法，可以提取有用的信息，除了传统的标记数据的辅助来源的发展。 这包括通过利用它们彼此相关的方式来快速学习多个相关任务的方法。 第二种方法是通过观察不同用户或代理的交互结果来了解他们想要什么。 最后，第三个重点涉及开发新的严格方法，用于快速估计解决给定学习任务所需的资源量。 该项目的更广泛影响包括培训多样化的研究生，改进与机器学习技术有关的本科课程，并为高年级本科生编写一本关于数据科学算法和分析的新书。更具体地说，这项工作的第一个主要目标涉及无监督，半监督和多任务学习的组合。这项工作将研究从未标记数据中估计错误率，统一协同训练和主题模型，从有限的监督中学习多个相关任务，以及使用高维几何工具学习新的数据表示方法等问题。 第二个主要重点将集中在重建估计代理效用从观察的经济机制，如组合拍卖的结果。 这个推力还包括从实验中学习未知机制的规则的问题。 最后，最后一个重点是机器学习问题的属性测试理论的发展，目标是快速估计给定学习任务的复杂性的自然形式度量。

项目成果

Algorithms for Generalized Topic Modeling

• DOI: 10.1609/aaai.v32i1.11825
• 发表时间: 2018-04
• 作者: Avrim Blum;Nika Haghtalab

Diversified Strategies for Mitigating Adversarial Attacks in Multiagent Systems

• DOI: 10.5555/3237383.3237446
• 发表时间: 2018-07
• 期刊: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 作者: Maria-Florina Balcan;Avrim Blum;Shang-Tse Chen

On Price versus Quality

关于价格与质量

• 发表时间: 2018
• 期刊: ITCS 2018
• 作者: Blum, Avrim;Mansour, Yishay
• 通讯作者: Mansour, Yishay