CIF: Medium: Learning, refining, and understanding models through relational feedback

CIF：中：通过关系反馈学习、完善和理解模型

• 批准号: 2107455
• 负责人: Mark Davenport
• 金额: $ 50万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2025-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2107455&HistoricalAwards=false
• 关键词: CIF; Medium; Learning; refining; understanding

Most machine intelligence systems require cooperation between a learning algorithm and an oracle expert providing supervision. There are many rich learning scenarios in which data from the oracle consists of relational feedback, either in terms of partial orders or preferences among items, labels indicating the perception of similarity or differences between items, or rich combinations thereof when the oracle executes a sequence of decisions to optimize her own utility. In all of these settings, there is a data space that is implicit to the oracle, and the investigators wish to exploit structure in this space (i.e., learn), to judiciously elicit and combine knowledge from a variety of data sources to accelerate this process (i.e., refine), and to transfer aspects of this structure into other learned models (i.e., understand). The investigators propose a collaborative research agenda that will transform the ability to learn, refine, and understand models through relational feedback in two distinct ways: (a) by exploiting latent space representations to build better models and algorithms, and (b) by exploiting new relational query paradigms for more efficient, effective, and interpretable information extraction from oracles. The investigators are involving students at all levels and across multiple departments in this highly interdisciplinary research effort that is expected to have broad applications, including (but not limited to) information-retrieval systems, (inverse) reinforcement learning, and psychophysical experimental design. The results of the proposed research are intended to improve the understanding of ranking systems impacting how content is displayed on news and social media sites, and even how hiring and college admissions is conducted. The researchers also intend to develop new tools for aggregating subjective human preferences that use relational queries to align AI systems with human values. Additionally, the PIs are devoting resources from this project to broaden participation among traditionally under-represented groups.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.

大多数机器智能系统需要学习算法和提供监督的Oracle专家之间的合作。在许多丰富的学习场景中，当Oracle执行一系列决策以优化她自己的效用时，来自Oracle的数据由关系反馈、指示项目之间的相似性或差异的感知的标签、或它们的丰富组合组成。在所有这些设置中，有一个对先知来说是隐含的数据空间，调查人员希望利用这个空间中的结构(即，学习)，明智地从各种数据来源获取和组合知识，以加速这一过程(即，改进)，并将这种结构的各个方面转移到其他学习模型中(即，理解)。研究人员提出了一个合作研究议程，它将以两种不同的方式转变通过关系反馈学习、改进和理解模型的能力：(A)通过利用潜在空间表示来构建更好的模型和算法，以及(B)通过利用新的关系查询范例来更高效、有效和可解释地从先知中提取信息。研究人员让所有级别和多个系的学生参与这项高度跨学科的研究工作，预计将有广泛的应用，包括(但不限于)信息检索系统、(反向)强化学习和心理物理实验设计。拟议中的研究结果旨在提高人们对排名系统的理解，排名系统会影响内容在新闻和社交媒体网站上的显示方式，甚至会影响招聘和大学招生的方式。研究人员还打算开发新的工具来聚合人类的主观偏好，这些偏好使用关系查询来使人工智能系统与人类价值观保持一致。此外，PIs正在从这个项目中投入资源，以扩大传统上代表不足的群体的参与。这一奖项反映了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

What governs attitudes toward artificial intelligence adoption and governance?

什么决定了人们对人工智能采用和治理的态度？

• DOI: 10.1093/scipol/scac056
• 发表时间: 2022
• 期刊: Science and Public Policy
• 影响因子: 2.7
• 作者: O’Shaughnessy, Matthew R.;Schiff, Daniel S.;Varshney, Lav R.;Rozell, Christopher J.;Davenport, Mark A.
• 通讯作者: Davenport, Mark A.

Optimal Convex Lifted Sparse Phase Retrieval and PCA With an Atomic Matrix Norm Regularizer

• DOI: 10.1109/tit.2022.3228508
• 发表时间: 2021-11
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Andrew D. McRae;J. Romberg;M. Davenport

Sharp analysis of EM for learning mixtures of pairwise differences

敏锐的 EM 分析，用于学习成对差异的混合

• 发表时间: 2023
• 期刊: Proceedings of Thirty Sixth Conference on Learning Theory
• 作者: Dhawan, Abhishek;Mao, Cheng;Pananjady, Ashwin
• 通讯作者: Pananjady, Ashwin

Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning

低秩度量学习的感知调整查询和倒置测量范式

• 发表时间: 2023
• 期刊: Advances in neural information processing systems
• 作者: Austin Xu;Andrew McRae;Jingyan Wang;Mark Davenport;Ashwin Pananjady
• 通讯作者: Ashwin Pananjady

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation

马尔可夫线性随机逼近的最优且依赖于实例的保证

• 发表时间: 2022
• 期刊: Proceedings of the 35th Conference on Learning Theory (COLT2022
• 作者: Mou, Wenlong;Pananjady, Ashwin;Wainwright, Martin J.;Bartlett, Peter L.
• 通讯作者: Bartlett, Peter L.