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

AF: Small: Learning Theory for a Modern World: Transfer Learning, Unsupervised Learning, and Beyond Prediction

AF：小：现代世界的学习理论：迁移学习、无监督学习和超越预测

基本信息

批准号：
1910321
负责人：
Maria-Florina Balcan
金额：
$ 39.98万
依托单位：
Carnegie-Mellon University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-10-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1910321&HistoricalAwards=false
关键词：
AF Small Learning Theory Modern

项目摘要

Machine learning studies the design of automatic methods for extracting information from data. It is a highly successful technique that has transformed several fields including computer vision and information retrieval, and it holds great promise to transform many other areas across science and technology. This project aims to substantially advance machine learning by providing new theoretical foundations and algorithms that are required both for new applications and to cope with the current massive amounts of available data. This includes developing well founded techniques for learning more complex objects (than classic techniques that are often limited to prediction), learning from very small amounts of annotated training data, and efficient transfer (of representations and other useful information) among tasks in order to aid more efficient learning of future tasks. These topics are of significant practical importance and expose fundamental statistical and computational issues. This project will impact not only theory of computing and machine learning, but also many application areas where machine learning is used. In addition to advising both graduate and undergraduate students on topics connected to this project, research progress will be integrated in the curricula of several courses at Carnegie Mellow University and course materials will be made available on the web worldwide.The key research directions of this project are: (1)Providing formal guarantees and algorithms for transferring internal representations (such as a portion of a deep network) learned while solving an earlier task to new related tasks, in ways that can significantly reduce both data requirements and run-time for solving the new tasks. This project will analyze both a direct transfer of a learned representation, and additional fine-tuning steps using a small amount of data from the new task.(2)Developing foundations and algorithms for transfer learning in unsupervised and partially supervised learning scenarios, in order to reduce reliance on difficult-to-verify assumptions in cases where labeled data is scarce.(3)Developing new algorithms for online learning of complex, non-convex functions, which do not satisfy standard conditions such as convexity or Lipschitzness. This project will consider online learning of such functions under various forms of feedback, including full information, bandit, and semi-bandit settings, and will also explore implications of these techniques to transfer learning in partially supervised scenarios.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.

机器学习研究从数据中提取信息的自动方法的设计。这是一项非常成功的技术，已经改变了包括计算机视觉和信息检索在内的几个领域，而且它很有希望在科学和技术领域改变许多其他领域。该项目旨在通过提供新的理论基础和算法来大幅推进机器学习，这些新的理论基础和算法既是新的应用所需的，也是处理当前大量可用数据所需的。这包括开发有充分基础的技术来学习更复杂的对象(与通常仅限于预测的经典技术相比)、从非常少量的注释训练数据中学习、以及任务之间的有效传输(表示和其他有用信息)，以帮助更有效地学习未来的任务。这些专题具有重要的实践意义，暴露了基本的统计和计算问题。该项目不仅将影响计算和机器学习的理论，而且将影响使用机器学习的许多应用领域。除了就与该项目相关的主题向研究生和本科生提供建议外，研究进展将被整合到卡内基梅洛大学的几门课程的课程中，课程材料将在全球范围内提供。该项目的主要研究方向是：(1)提供形式保证和算法，将在解决较早任务时学习的内部表示(如深度网络的一部分)转移到新的相关任务，以显著减少解决新任务的数据要求和运行时间。这个项目将分析学习表示的直接迁移，以及使用新任务中的少量数据进行额外的微调步骤。(2)开发无监督和部分监督学习场景中的迁移学习的基础和算法，以减少对难以验证的假设的依赖，以便在标记数据稀缺的情况下。(3)开发新的算法，用于在线学习复杂的非凸函数，这些函数不满足标准条件，如凸性或Lipschitzness。这个项目将考虑在各种形式的反馈下在线学习这些功能，包括完全信息、强盗和半强盗环境，并将探索这些技术在部分监督场景中转移学习的影响。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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（18）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Learning Predictions for Algorithms with Predictions

通过预测来学习算法的预测

DOI：
发表时间：
2022
期刊：
Advances in Neural Information Processing Systems
影响因子：
0
作者：
Khodak, Mikhail;Balcan, Maria Florina;Talwalkar, Ameet;Vassilvitskii, Sergei
通讯作者：
Vassilvitskii, Sergei

Learning piecewise Lipschitz functions in changing environments

DOI：
发表时间：
2019-07
期刊：
影响因子：
0
作者：
Dravyansh Sharma;Maria-Florina Balcan;Travis Dick
通讯作者：
Dravyansh Sharma;Maria-Florina Balcan;Travis Dick

Learning to Link

学习链接

DOI：
发表时间：
2020
期刊：
International Conference on Learning Representation
影响因子：
0
作者：
Balcan, Maria-Florina;Dick, Travis;Lang, Manuel
通讯作者：
Lang, Manuel

How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design

DOI：
10.1145/3406325.3451036
发表时间：
2021-06
期刊：
Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing
影响因子：
0
作者：
Maria-Florina Balcan;Dan F. DeBlasio;Travis Dick;Carl Kingsford;T. Sandholm;Ellen Vitercik
通讯作者：
Maria-Florina Balcan;Dan F. DeBlasio;Travis Dick;Carl Kingsford;T. Sandholm;Ellen Vitercik

Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games

对抗鲁棒性博弈中的纳什均衡和对抗训练的陷阱

DOI：
发表时间：
2023
期刊：
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics
影响因子：
0
作者：
Balcan, Maria-Florina;Pukdee, Rattana;Ravikumar, Pradeep;Zhang, Hongyang
通讯作者：
Zhang, Hongyang