New Studies of Learning with Stochastic Convex Optimization
随机凸优化学习的新研究
基本信息
- 批准号:2110836
- 负责人:
- 金额:$ 15万
- 依托单位:
- 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:2021-08-01 至 2024-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The paradigm of learning from data is playing an increasingly important role in science and engineering. The interplay between machine learning and mathematical optimization has been most fruitful, and one prominent area is stochastic convex optimization (SCO). However, there is relatively little work on the fundamental questions such as generalization and stability analysis, and the existing studies often focus on the standard classification and regression with smooth losses. Furthermore, data collected and used for the learning often contains sensitive information such as financial records from fraud detection or genomic data from cancer diagnosis which presents an urgent need to develop privacy-preserving SCO algorithms with theoretical guarantees. These provide motivation for the project which aims to study the fundamental properties of machine learning inspired SCO algorithms including their stability, generalization, and differential privacy. Students will be involved and trained in interdisciplinary aspects. The technical objectives of the proposed work are divided into three thrusts. The first thrust focuses on the study of stability and generalization of stochastic gradient methods (SGM) for solving SCO problems associated with non-smooth losses. The second thrust is to develop and study SGM algorithms for SCO problems which can prevent the privacy leakage using a well-accepted mathematical definition of privacy called differential privacy. The third thrust is to study the stability, generalization, and differential privacy of SCO algorithms for pairwise learning which involves more complex losses than the standard classification and regression.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.
从数据中学习的范式在科学和工程中发挥着越来越重要的作用。机器学习和数学优化之间的相互作用是最有成效的,其中一个突出的领域是随机凸优化(SCO)。然而,对泛化和稳定性分析等基本问题的研究相对较少,现有的研究往往集中在具有平滑损失的标准分类和回归上。此外,收集并用于学习的数据往往包含敏感信息,如欺诈检测的财务记录或癌症诊断的基因组数据,这表明迫切需要开发具有理论保障的隐私保护SCO算法。这些都为该项目提供了动机,该项目旨在研究受机器学习启发的SCO算法的基本属性,包括它们的稳定性、泛化和差异隐私。学生将参与并接受跨学科方面的培训。拟议工作的技术目标分为三个重点。第一个重点是研究随机梯度法(SGM)求解与非光滑损失相关的SCO问题的稳定性和泛化能力。第二个重点是开发和研究解决SCO问题的SGM算法,该算法可以使用一个被广泛接受的隐私的数学定义--差异隐私来防止隐私泄露。第三个重点是研究SCO成对学习算法的稳定性、泛化和差异隐私,这涉及到比标准分类和回归更复杂的损失。该奖项反映了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
期刊论文数量(13)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Unmixing Biological Fluorescence Image Data with Sparse and Low-Rank Poisson Regression
- DOI:10.1101/2023.01.06.523044
- 发表时间:2023-01
- 期刊:
- 影响因子:0
- 作者:Ruogu Wang;A. Lemus;Colin M. Henneberry;Yiming Ying;Yunlong Feng;A. Valm
- 通讯作者:Ruogu Wang;A. Lemus;Colin M. Henneberry;Yiming Ying;Yunlong Feng;A. Valm
Differentially Private SGDA for Minimax Problems
- DOI:
- 发表时间:2022-01
- 期刊:
- 影响因子:0
- 作者:Zhenhuan Yang;Shu Hu;Yunwen Lei;Kush R. Varshney;Siwei Lyu;Yiming Ying
- 通讯作者:Zhenhuan Yang;Shu Hu;Yunwen Lei;Kush R. Varshney;Siwei Lyu;Yiming Ying
AUC Maximization in the Era of Big Data and AI: A Survey
- DOI:10.1145/3554729
- 发表时间:2023-08-01
- 期刊:
- 影响因子:16.6
- 作者:Yang,Tianbao;Ying,Yiming
- 通讯作者:Ying,Yiming
Minimax AUC Fairness: Efficient Algorithm with Provable Convergence
Minimax AUC 公平性:具有可证明收敛性的高效算法
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Yang, Zhenhuan;Ko, Yan Lok;Varshney, Kush R;Ying, Yiming
- 通讯作者:Ying, Yiming
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
- DOI:
- 发表时间:2021-12
- 期刊:
- 影响因子:0
- 作者:Dixian Zhu;Yiming Ying;Tianbao Yang
- 通讯作者:Dixian Zhu;Yiming Ying;Tianbao Yang
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Zi Yang其他文献
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
CoMERA:通过排名自适应张量优化进行计算和内存高效训练
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Zi Yang;Samridhi Choudhary;Xinfeng Xie;Cao Gao;Siegfried Kunzmann;Zheng Zhang - 通讯作者:
Zheng Zhang
Analysis and validation method for polarization phenomena based on acoustic vector Hydrophones
基于声矢量水听器的极化现象分析与验证方法
- DOI:
10.1016/j.apacoust.2025.110669 - 发表时间:
2025-05-14 - 期刊:
- 影响因子:3.600
- 作者:
Zi Yang;Erzheng Fang - 通讯作者:
Erzheng Fang
The Jieduquyuziyin prescription alleviates systemic lupus erythematosus by modulating B cell metabolic reprogramming via the AMPK/PKM2 signaling pathway
解毒去瘀滋饮方通过 AMPK/PKM2 信号通路调节 B 细胞代谢重编程来减轻系统性红斑狼疮。
- DOI:
10.1016/j.jep.2025.119626 - 发表时间:
2025-04-09 - 期刊:
- 影响因子:5.400
- 作者:
Xiaolong Li;Qingmiao Zhu;Zi Yang;Mengyu Zhu;ZhiJun Xie;Yongsheng Fan;Ting Zhao - 通讯作者:
Ting Zhao
Shrub removal suppresses the effects of warming on nematode communities in an alpine grassy ecosystem
灌木清除抑制了变暖对高山草原生态系统中线虫群落的影响
- DOI:
10.1016/j.apsoil.2025.106117 - 发表时间:
2025-07-01 - 期刊:
- 影响因子:5.000
- 作者:
Zi Yang;Jingwei Chen;Jiajia Wang;Ziyang Liu;Lihua Meng;Hanwen Cui;Sa Xiao;Anning Zhang;Kun Liu;Lizhe An;Shuyan Chen;Uffe N. Nielsen - 通讯作者:
Uffe N. Nielsen
Insight into the corrosion inhibition performance of triethylenetetramine (TETA) for AZ31 Mg alloy
三乙烯四胺(TETA)对 AZ31 镁合金缓蚀性能的研究
- DOI:
10.1016/j.colsurfa.2025.136246 - 发表时间:
2025-04-05 - 期刊:
- 影响因子:5.400
- 作者:
Liyan Wang;Sifan Tu;Keqi Huang;Honglei Guo;Bing Lei;Zi Yang;Qiwen Yong;Zhiyuan Feng;Xiaotao Liu;Guozhe Meng - 通讯作者:
Guozhe Meng
Zi Yang的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似海外基金
Using clinical polysomnography data and machine learning to determine minimum sensing requirements for pediatric sleep studies
使用临床多导睡眠图数据和机器学习来确定儿科睡眠研究的最低传感要求
- 批准号:
491364 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Operating Grants
Supporting Engineering and Computing Studies Scholars through Experiential Learning, Personal Development, and Community Service
通过体验式学习、个人发展和社区服务支持工程和计算机研究学者
- 批准号:
2221052 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
A Study about Intellectual, Social, and Emotional Learning in Living Environment Studies
生活环境研究中智力、社会和情感学习的研究
- 批准号:
23K02456 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Teacher accountability to improve learning outcomes; synthesis of 4 RLO-studies
教师对改善学习成果负有责任;
- 批准号:
ES/X013987/1 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Research Grant
Decrypting the genetic architecture of heart failure imaging signatures through machine learning in large-scale genome-wide association studies
在大规模全基因组关联研究中通过机器学习解密心力衰竭成像特征的遗传结构
- 批准号:
MR/X020924/1 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Fellowship
Studies in machine learning and robotics for automated construction
用于自动化施工的机器学习和机器人技术研究
- 批准号:
2891648 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Studentship
Developing a blood fatty acid-based algorithm as an early predictor of insulin resistance: Applying machine learning to harmonized data from prospective cohort studies
开发基于血液脂肪酸的算法作为胰岛素抵抗的早期预测因子:将机器学习应用于前瞻性队列研究的统一数据
- 批准号:
10696711 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Bayesian machine learning for complex missing data and causal inference with a focus on cardiovascular and obesity studies
用于复杂缺失数据和因果推理的贝叶斯机器学习,重点关注心血管和肥胖研究
- 批准号:
10563598 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Learn, transfer, generate: Developing novel deep learning models for enhancing robustness and accuracy of small-scale single-cell RNA sequencing studies
学习、转移、生成:开发新颖的深度学习模型,以增强小规模单细胞 RNA 测序研究的稳健性和准确性
- 批准号:
10535708 - 财政年份:2023
- 资助金额:
$ 15万 - 项目类别:
Studies of individual optimal learning in sewing classes applying Swedish craft education
应用瑞典工艺教育的缝纫班个体最佳学习研究
- 批准号:
22K20229 - 财政年份:2022
- 资助金额:
$ 15万 - 项目类别:
Grant-in-Aid for Research Activity Start-up