III: Small: Collaborative Learning with Incomplete and Noisy Knowledge

III：小：知识不完整且有噪音的协作学习

基本信息

批准号：
1904183
负责人：
Quanquan Gu
金额：
$ 35.09万
依托单位：
University of California-Los Angeles
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：
2018-07-01 至 2021-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1904183&HistoricalAwards=false
关键词：
III Small Collaborative Learning Incomplete

项目摘要

The accelerated growth of Big Data has created enormous amount of information at the macro level for knowledge discovery. But at the micro level, one can only expect a handful of observations in most individual users. This hinders the exploration of subtle patterns and heterogeneities among distinct users for improving the utility of Big Data analytics at a per-user basis. The objective of this project is to develop a set of algorithmic solutions to perform online learning in a collaborative fashion, where personalized learning solutions actively interact with users for feedback acquisition and collaborate with each other to learn from incomplete and noisy input. This project amplifies the utility of statistical learning in many important fields, such as healthcare, business intelligence, crowdsourcing, and cyber physical systems, where automated decision models are built on diverse, noisy and heterogeneous supervision. The research activities will be incorporated into teaching materials for student training and education in the areas of information retrieval, machine learning and data mining. This project consists of three synergistic research thrusts. First, it develops a family of contextual bandit algorithms to perform collaborative online learning over networked users. Dependency among users is estimated and exploited to collaboratively update the individualized bandit parameters. Second, it develops principled solutions to optimize task-specific and general loss functions for online learning, which enables the collaborative learning solutions reach more important real-world applications, such as information retrieval and user behavior modeling. Third, it models and differentiates the reliability of the sources of feedback to optimize the overall online learning effectiveness, which is especially important in the applications such as health informatics, crowdsourcing and cyber physical systems. Expected outcomes of the project include: 1) open source implementations for the developed online learning solutions; and 2) evaluation corpora that will enable researchers to conduct follow-up research in related domains.

大数据的加速增长为知识发现创造了宏观层面的海量信息。但在微观层面上，我们只能期望在大多数个人用户中得到少量的观察结果。这阻碍了对不同用户之间微妙模式和异质性的探索，以提高每个用户的大数据分析的实用性。该项目的目标是开发一套算法解决方案，以协作方式执行在线学习，其中个性化学习解决方案积极与用户交互以获取反馈，并相互协作从不完整和嘈杂的输入中学习。该项目扩大了统计学习在许多重要领域的效用，例如医疗保健、商业智能、众包和网络物理系统，其中自动化决策模型建立在多样化、嘈杂和异构的监督之上。研究活动将被纳入信息检索、机器学习和数据挖掘领域学生培训和教育的教材中。该项目由三个协同研究重点组成。首先，它开发了一系列上下文强盗算法，以通过网络用户执行协作在线学习。估计并利用用户之间的依赖性来协作更新个性化老虎机参数。其次，它开发了原则性的解决方案来优化在线学习的特定任务和一般损失函数，这使得协作学习解决方案能够达到更重要的现实应用，例如信息检索和用户行为建模。第三，它对反馈源的可靠性进行建模和区分，以优化整体在线学习效果，这在健康信息学、众包和网络物理系统等应用中尤其重要。该项目的预期成果包括：1）开发的在线学习解决方案的开源实现； 2）评估语料库，使研究人员能够在相关领域进行后续研究。

项目成果

期刊论文数量（19）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

使用线性函数逼近学习无限视野平均奖励 MDP 的近极小极大最优遗憾

DOI：
发表时间：
2021-02-15
期刊：
影响因子：
0
作者：
Yue Wu;Dongruo Zhou;Quanquan Gu
通讯作者：
Quanquan Gu

Logarithmic Regret for Reinforcement Learning with Linear Function Approximation

线性函数逼近强化学习的对数遗憾

DOI：
10.48550/arxiv.2306.07745
发表时间：
2020-11-23
期刊：
ArXiv
影响因子：
0
作者：
Jiafan He;Dongruo Zhou;Quanquan Gu
通讯作者：
Quanquan Gu

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

贴现 MDP 的近极小极大最优强化学习

DOI：
发表时间：
2021-01
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
He, Jiafan;Zhou, Dongruo;Gu, Quanquan
通讯作者：
Gu, Quanquan

Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs

用于学习对抗性线性混合 MDP 的近最优策略优化算法

DOI：
10.1109/apsipa.2017.8282190
发表时间：
2021-02-17
期刊：
2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
影响因子：
0
作者：
Jiafan He;Dongruo Zhou;Quanquan Gu
通讯作者：
Quanquan Gu

Learning Neural Contextual Bandits through Perturbed Rewards

通过扰动奖励学习神经情境强盗