CCF-BSF: AF: Small: Algorithms for Interactive Learning

CCF-BSF：AF：小型：交互式学习算法

• 批准号: 1813160
• 负责人: Sanjoy Dasgupta
• 金额: $ 50万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-06-01 至 2022-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1813160&HistoricalAwards=false
• 关键词: CCF; BSF; AF; Small; Algorithms

Machine learning classifiers are core components of many of the technologies we use routinely: search engines, speech recognition engines, language translators, assisted driving systems, and so on. These classifiers are typically built by a process of 'supervised learning', in which a computer is given a collection of (input, output) pairs that illustrate a desired behavior (e.g. if the input is this English sentence, the output should be this Spanish sentence) and is told to produce a function that replicates such behavior. This is a rigid form of learning that is known to suffer from a variety of fundamental hurdles; for instance, there are classes of concepts that cannot efficiently be learned in this way. This project will study how such hurdles can be overcome by moving to a more natural learning setup, in which the learning machine is allowed to interact with a human while learning, and receives feedback that is richer than just output values. This research has the potential to influence the way in which machine learning is performed and to broaden its scope of applicability. It is inherently multidisciplinary, and thus part of the project includes community-building activities that will bring together different groups of relevant researchers. There is also an educational component to the project, centered on bringing knowledge of algorithms and machine learning to various student groups that have traditionally been under-represented in STEM disciplines. Interactive learning is a field with great promise in which most of the work to date has consisted of one-off systems geared towards specific applications. This project will aim to bring rigor, formalism, and algorithms with provable guarantees to parts of this field that are currently lacking them.This project will aim to formalize forms of human feedback (to a learning machine) than are richer than those traditionally studied, such as: simple explanations (e.g. this bird is not a canary because it has the wrong type of beak); attention-focusing; and similarity judgments. The investigators will design algorithms that are able to use these kinds of feedback and have rigorous guarantees, both on correctness and on statistical rates of convergence. The project is particularly focused on overcoming fundamental hardness barriers in learning: learning concept classes that would be intractable to learn in the usual supervised framework; learning with dramatically fewer examples than would normally be needed; adapting to situations in which the distribution of the data is constantly shifting; and improving the results of unsupervised learning.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.

机器学习分类器是我们日常使用的许多技术的核心组件：搜索引擎、语音识别引擎、语言翻译器、辅助驾驶系统等。这些分类器通常通过“监督学习”过程构建，在该过程中，计算机被给予一组（输入，输出）对，其说明期望的行为（例如，如果输入是这个英语句子，则输出应该是这个西班牙语句子）并且被告知产生复制这种行为的函数。这是一种严格的学习形式，已知会受到各种基本障碍的影响;例如，有些概念无法以这种方式有效地学习。该项目将研究如何通过转向更自然的学习设置来克服这些障碍，在这种设置中，允许学习机器在学习时与人类互动，并接收比输出值更丰富的反馈。这项研究有可能影响机器学习的执行方式，并扩大其适用范围。它本身就是多学科的，因此，该项目的一部分包括社区建设活动，将不同的相关研究人员群体聚集在一起。该项目还有一个教育部分，重点是将算法和机器学习的知识带给传统上在STEM学科中代表性不足的各种学生群体。交互式学习是一个有很大希望的领域，其中大部分的工作迄今为止已经包括面向特定应用的一次性系统。该项目旨在为该领域目前缺乏的部分带来严谨性、形式主义和可证明保证的算法。该项目旨在将人类反馈的形式化（给学习机器），这些形式比传统研究的形式更丰富，例如：简单的解释（例如，这只鸟不是金丝雀，因为它有错误的喙型）;注意力集中;以及相似性判断。研究人员将设计能够使用这些反馈的算法，并在正确性和统计收敛率方面都有严格的保证。该项目特别关注克服学习中的基本困难障碍：学习在通常的监督框架中难以学习的概念类;使用比通常需要的少得多的示例进行学习;适应数据分布不断变化的情况;该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的评估来支持。影响审查标准。

项目成果

An adaptive nearest neighbor rule for classification

• 发表时间: 2019-05
• 期刊: International Journal of Radiation Oncology*Biology*Physics
• 作者: Akshay Balsubramani;S. Dasgupta;Y. Freund;S. Moran

Robust learning from discriminative feature feedback

从判别性特征反馈中进行稳健学习

• 发表时间: 2020
• 期刊: International Conference on Artificial Intelligence and Statistics
• 作者: Dasgupta, S.;Sabato, S.
• 通讯作者: Sabato, S.

A Non-Parametric Test to Detect Data-Copying in Generative Models

• 发表时间: 2020-04
• 期刊: ArXiv
• 作者: Casey Meehan;Kamalika Chaudhuri;S. Dasgupta

Learning what to remember

• 发表时间: 2022-01
• 期刊: ArXiv
• 作者: Robi Bhattacharjee;G. Mahajan

Teaching a black-box learner

• 发表时间: 2019-05
• 期刊: ArXiv
• 作者: S. Dasgupta;Daniel J. Hsu;Stefanos Poulis;Xiaojin Zhu