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

RI: SMALL: Robust Inference and Influence in Dynamic Environments

RI：小：动态环境中的鲁棒推理和影响

基本信息

批准号：
1907907
负责人：
Lillian Ratliff
金额：
$ 36.6万
依托单位：
University of Washington
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：
2019-09-01 至 2023-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1907907&HistoricalAwards=false
关键词：
RI SMALL Robust Inference Influence

项目摘要

Many application domains, such as online content recommendation, medical trials, and logistics and operations in intelligent infrastructure require the practitioner to sequentially make decisions given little information about the environment and the optimality of selected actions.On a limited measurement budget, adaptive data collection can make the difference between measuring a phenomenon, or missing it. Recent advances in machine learning have provided rich insights into ways of using past observations to guide planning of future measurements. Most state-of-the-art approaches assume observations arise from an environment with fixed probabilistic characteristics. Yet, in practice, environments such as these tend to be the exception and not the rule. To handle this, practitioners supplement existing algorithms with ad-hoc exceptions and rule of thumb mechanisms, but relying on heuristics to account for brittle assumptions may itself be brittle and call into question the entire experiment. The objective of this project is to develop algorithms with performance guarantees for collecting data adaptively in dynamic and unpredictable environments with the goal of making robust inferences, faster and cheaper.The technical agenda of this project will advance the state-of-the-art by introducing a contextual non-stochastic pure exploration framework that extends recent advances in context-free non-stochastic best-arm identification, and exploits available contextual information when possible while simultaneously giving robust guarantees in non-stochastic environments. By taking a best-of-both-worlds approach, the project will also introduce resilience into the design of algorithms for adaptive inference and influence by building model misspecification into the framework. This will allow for simple models to be used as an approximate model for inference and influence when the model is accurate, but not mislead when it is not. The framework will also extend to hyperparameter tuning of machine learning models in the more challenging setting of contextual non-stationary or streaming-data environments (e.g., federated learning on mobile devices for ``edge computing'') thereby providing theoretical advancements with utility in several application domains. The project will conduct experiments informed by real world data in its development of a rigorous theoretical framework. Accompanying the technical agenda is an integrated research and education plan that includes cross-disciplinary undergrad and grad course development leveraging the experimental platform as well as student opportunities to engage with industry.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.

许多应用程序领域，如在线内容推荐、医疗试验以及智能基础设施中的物流和操作，都要求从业者在关于环境和所选操作的最优性信息很少的情况下依次做出决策。在有限的测量预算中，自适应数据收集可以在测量或遗漏现象之间产生差异。机器学习的最新进展为利用过去的观察来指导未来测量的规划提供了丰富的见解。大多数最先进的方法假设观测来自具有固定概率特征的环境。然而，在实践中，这样的环境往往是例外，而不是规则。为了解决这个问题，从业者用特殊的例外和经验法则机制来补充现有的算法，但是依靠启发式来解释脆弱的假设本身可能是脆弱的，并且会对整个实验产生疑问。该项目的目标是开发具有性能保证的算法，以便在动态和不可预测的环境中自适应地收集数据，目标是更快、更便宜地进行鲁棒推断。该项目的技术议程将通过引入上下文非随机纯勘探框架来推进最先进的技术，该框架扩展了上下文无关的非随机最佳臂识别的最新进展，并在可能的情况下利用可用的上下文信息，同时在非随机环境中提供强大的保证。通过采用两全其美的方法，该项目还将在自适应推理算法的设计中引入弹性，并通过将模型错误规范构建到框架中来产生影响。当模型准确时，这将允许使用简单模型作为推断和影响的近似模型，而当模型不准确时，则不会误导。该框架还将扩展到更具挑战性的上下文非平稳或流数据环境中机器学习模型的超参数调优（例如，用于“边缘计算”的移动设备上的联邦学习），从而在几个应用领域提供实用的理论进步。该项目将根据真实世界的数据进行实验，以建立严格的理论框架。伴随技术议程的是一项综合研究和教育计划，其中包括利用实验平台的跨学科本科和研究生课程开发以及学生与行业接触的机会。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值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 in Stochastic Monotone Games with Decision-Dependent Data

使用决策相关数据在随机单调博弈中学习

DOI：
发表时间：
2022
期刊：
The 25th International Conference on Artificial Intelligence and Statistics
影响因子：
0
作者：
Narang, A.;Faulkner, E.;Drusvyatskiy, D.;Fazel, M.;Ratliff, L.
通讯作者：
Ratliff, L.

Sequential Experimental Design for Transductive Linear Bandits

传导线性老虎机的序贯实验设计

DOI：
发表时间：
2019
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
Fiez, T.;Jain, L.;Jamieson, K.;Ratliff, L.J.
通讯作者：
Ratliff, L.J.

Multiplayer Performative Prediction: Learning in Decision-Dependent Games

多人表演预测：决策相关游戏中的学习

DOI：
发表时间：
2023
期刊：
Journal of machine learning research
影响因子：
6
作者：
Narang, Adhyyan;Faulkner, Evan;Drusvyatskiy, Dmitriy;Fazel, Maryam;Ratliff, Lillian J.
通讯作者：
Ratliff, Lillian J.

Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games

零和矩阵博弈的实例相关样本复杂度界限