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

RI: Small: Robustness and Confidence in Machine-Learned Systems

RI：小：机器学习系统的稳健性和信心

基本信息

批准号：
2006777
负责人：
John Duchi
金额：
$ 45万
依托单位：
Stanford University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-10-01 至 2023-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006777&HistoricalAwards=false
关键词：
RI Small Robustness Confidence Machine

项目摘要

The application of machine learning, in fields from medicine to mobile data gathering platforms, has substantial promise. Yet as data comes from a greater variety of sources in an ever-shifting world, how can one trust that machine-learned systems have not simply fit some strange idiosyncrasies they observe? This project develops methods for machine learning so that such systems are not brittle, sensitive to tiny changes in collected data, or likely to make critical mistakes on rare populations. With the growing importance of data analysis in science, industry, and healthcare, principled and practical approaches to robustness, safety, and calibration have immediate and wide-ranging effects. A major goal of the project is to provide decision makers with trustworthy predictions from machine-learned models. A second goal is pedagogical: with the meteoric rise of machine learning, there is a missed opportunity to educate students, researchers, and engineers to give them the ability to actually build trustworthy systems; this project aims toward a curriculum around such challenges.This project develops robust learning procedures in effort to build trustable machine learning. Three concrete thrusts underpin the work. The first builds off of the investigator's work in distributional robustness, which fits models to maximize performance on populations near enough to available data. The second is to use data creatively and correctly; this entails using the data to define robustness, understand method sensitivities, use unlabeled (cheap) data to build more robust representations, and construct data-based regularization. The third targets confidence and calibration, building models that provide assumption-free valid predictions. In this case, the aim is to seek predictors with calibrated confidence, building out of conformal prediction, which modern learning methods emphatically do not provide. More generally, distributional shifts challenge statistical machine learning methods, and the project aims for new validation and testing methodologies to understand such shifts, identify situations where methods are sensitive to changes in underlying data, and to allow valid confidence in predictions even in changing environments.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.

机器学习在从医学到移动的数据收集平台等领域的应用前景广阔。然而，在一个不断变化的世界中，数据来自更广泛的来源，人们怎么能相信机器学习系统不是简单地适应他们观察到的一些奇怪的特质呢？该项目开发了机器学习的方法，使这些系统不脆弱，对收集的数据中的微小变化不敏感，也不可能在稀有人群中犯严重错误。随着数据分析在科学、工业和医疗保健中的重要性日益增加，稳健性、安全性和校准的原则性和实用性方法具有直接和广泛的影响。该项目的一个主要目标是为决策者提供来自机器学习模型的可靠预测。第二个目标是教学：随着机器学习的迅速崛起，错过了教育学生、研究人员和工程师的机会，使他们能够真正构建可信赖的系统;本项目旨在围绕这些挑战开设课程。本项目开发了强大的学习程序，以努力构建可信赖的机器学习。三个具体的推力支撑着这项工作。第一个是建立在研究者在分布鲁棒性方面的工作基础上的，该工作适合模型，以最大限度地提高对足够接近可用数据的人群的性能。第二是创造性地正确使用数据;这需要使用数据来定义鲁棒性，理解方法敏感性，使用未标记（廉价）数据来构建更鲁棒的表示，并构建基于数据的正则化。第三个目标是信心和校准，建立模型，提供无干扰的有效预测。在这种情况下，目标是寻找具有校准置信度的预测器，建立在保形预测之外，而现代学习方法强调不提供。更一般地说，分布变化对统计机器学习方法提出了挑战，该项目旨在开发新的验证和测试方法，以了解这种变化，确定方法对基础数据变化敏感的情况，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知识产权进行评估来支持。优点和更广泛的影响审查标准。

项目成果

期刊论文数量（23）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization

DOI：
发表时间：
2021-01
期刊：
ArXiv
影响因子：
0
作者：
Karan N. Chadha;Gary Cheng;John C. Duchi
通讯作者：
Karan N. Chadha;Gary Cheng;John C. Duchi

Minibatch Stochastic Approximate Proximal Point Methods

DOI：
发表时间：
2020
期刊：
影响因子：
0
作者：
Hilal Asi;Karan N. Chadha;Gary Cheng;John C. Duchi
通讯作者：
Hilal Asi;Karan N. Chadha;Gary Cheng;John C. Duchi

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

DOI：
发表时间：
2020-02
期刊：
ArXiv
影响因子：
0
作者：
Aditi Raghunathan;Sang Michael Xie;Fanny Yang;John C. Duchi;Percy Liang
通讯作者：
Aditi Raghunathan;Sang Michael Xie;Fanny Yang;John C. Duchi;Percy Liang

Lower bounds for non-convex stochastic optimization

DOI：
10.1007/s10107-022-01822-7
发表时间：
2019-12
期刊：
Mathematical Programming
影响因子：
2.7
作者：
Yossi Arjevani;Y. Carmon;John C. Duchi;Dylan J. Foster;N. Srebro;Blake E. Woodworth
通讯作者：
Yossi Arjevani;Y. Carmon;John C. Duchi;Dylan J. Foster;N. Srebro;Blake E. Woodworth

Lower bounds for finding stationary points I