RI: Small: A Study of New Aggregate Losses for Machine Learning
RI:小:机器学习新总损失的研究
基本信息
- 批准号:2008532
- 负责人:
- 金额:$ 45万
- 依托单位:
- 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 2020-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Machine learning is instrumental for the recent advances in AI and big data analysis. They have been used in almost every area of computer science and many fields of natural sciences, engineering, and social sciences. The central task of machine learning is to “train” a model, which entails seeking models that minimize certain performance metrics over a set of training examples. Such performance metrics are termed as the aggregate losses, which are to be distinguished from the individual losses that measures the quality of the model on a single training example. As the link between the training data and the model to be learned, the aggregate loss is a fundamental component in machine learning algorithms, and its theoretical and practical significance warrants a comprehensive and systematic study. The proposed work will focus on several fundamental research questions concerning the aggregate loss: are there any other types of aggregate loss beyond the average individual losses?; if so, what will be a general abstract formulation of these new aggregate loss?; how can the new aggregate losses be adapted to different machine learning problems?; and what are the statistical and computational behaviors of machine learning algorithms using the general aggregate losses?. The technical aims of the project are divided into four interrelated thrusts. The first thrust explores new types of rank-based aggregate losses for binary classification and study efficient algorithms optimizing learning objectives formed based upon them. The new aggregate losses will be applied to problems such as object detection, where rank-based evaluation metric is used dominantly. The second thrust aims to deepen our understanding of the binary classification algorithms developed using the rank-based aggregate losses and will be focused on a study of their statistical theories such as generalization and consistency. The third thrust will extend the study of new types of aggregate losses to other supervised problems (multi-class and multi-label learning and supervised metric learning) and unsupervised learning. The fourth thrust dedicates to the theoretical aspects of aggregate losses, in which an aggregate loss will be abstracted as a set function that maps the ensemble of individual losses to a number. This abstraction will be exploited to study the properties of new aggregate losses that make them superior than the average loss and propose new aggregate losses beyond rank-based ones.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.
机器学习对人工智能和大数据分析的最新进展至关重要。它们已经被用于计算机科学的几乎每个领域以及自然科学、工程和社会科学的许多领域。机器学习的中心任务是“训练”模型,这需要在一组训练示例中寻找最小化某些性能指标的模型。这样的性能指标被称为总损失,它与在单个训练示例上测量模型质量的个体损失不同。聚合损失作为连接训练数据和待学习模型的纽带,是机器学习算法中的一个基本组成部分,其理论和实际意义值得进行全面系统的研究。拟议的工作将集中在几个基本的研究问题有关的总损失:是否有任何其他类型的总损失以外的平均个人损失?如果是,这些新的总损失的一般抽象公式是什么?新的总损失如何适应不同的机器学习问题?以及使用一般总损失的机器学习算法的统计和计算行为是什么?该项目的技术目标分为四个相互关联的重点。第一个推力探索了二进制分类的基于秩的聚合损失的新类型,并研究了优化基于它们形成的学习目标的有效算法。新的总损失将被应用到问题,如对象检测,其中基于排名的评估指标是占主导地位。第二个推力旨在加深我们对使用基于秩的总损失开发的二进制分类算法的理解,并将重点研究其统计理论,如泛化和一致性。第三个重点是将新类型的总损失的研究扩展到其他监督问题(多类和多标签学习和监督度量学习)和无监督学习。第四个推力致力于理论方面的综合损失,其中一个综合损失将抽象为一组函数,映射到一个数字的个人损失的合奏。这个抽象将被利用来研究新的总损失的属性,使他们比平均损失上级,并提出新的总损失超越排名为基础的。这个奖项反映了NSF的法定使命,并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。
项目成果
期刊论文数量(17)
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 by Minimizing the Sum of Ranked Range
- DOI:
- 发表时间:2020-10
- 期刊:
- 影响因子:0
- 作者:Shu Hu;Yiming Ying;Xin Wang;Siwei Lyu
- 通讯作者:Shu Hu;Yiming Ying;Xin Wang;Siwei Lyu
Stability and differential privacy of stochastic gradient descent for pairwise learning with non-smooth loss
非平滑损失成对学习的随机梯度下降的稳定性和差分隐私
- DOI:
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Yang, Zhenhuan;Lei, Yunwen;Lyu, Siwei;Ying, Yiming
- 通讯作者:Ying, Yiming
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
Stability and Generalization for Markov Chain Stochastic Gradient Methods
- DOI:10.48550/arxiv.2209.08005
- 发表时间:2022-09
- 期刊:
- 影响因子:0
- 作者:Puyu Wang;Yunwen Lei;Yiming Ying;Ding-Xuan Zhou
- 通讯作者:Puyu Wang;Yunwen Lei;Yiming Ying;Ding-Xuan Zhou
{{
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 }}
Siwei Lyu其他文献
Countering JPEG anti-forensics based on noise level estimation
基于噪声水平估计的 JPEG 反取证对抗
- DOI:
10.1007/s11432-016-0426-1 - 发表时间:
2017-08 - 期刊:
- 影响因子:0
- 作者:
Hui Zeng;Xiangui Kang;Jingjing Yu;Siwei Lyu - 通讯作者:
Siwei Lyu
Online Deformable Object Tracking Based on Structure-Aware Hyper-Graph
基于结构感知超图的在线变形目标跟踪
- DOI:
10.1109/tip.2016.2570556 - 发表时间:
2016-08 - 期刊:
- 影响因子:10.6
- 作者:
Dawei Du;Honggang Qi;Wenbo Li;Longyin Wen;Qingming Huang;Siwei Lyu - 通讯作者:
Siwei Lyu
Deep Constrained Low-Rank Subspace Learning for Multi-View Semi-Supervised Classification
用于多视图半监督分类的深度约束低秩子空间学习
- DOI:
10.1109/lsp.2019.2923857 - 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
Zhe Xue;Junping Du;Dawei Du;Guorong Li;Qingming Huang;Siwei Lyu - 通讯作者:
Siwei Lyu
Vertebral artery course variation leading to an insufficient proximal anchoring area for thoracic endovascular aortic repair.
椎动脉走行变化导致胸主动脉腔内修复的近端锚固区域不足。
- DOI:
10.1177/17085381221140319 - 发表时间:
2022 - 期刊:
- 影响因子:1.1
- 作者:
Zuanbiao Yu;Siwei Lyu;Dehai Lang;Di Wang;Songjie Hu;Xiaoliang Yin;Yunpeng Ding;Chunbo Xu;Chen Lin;Jiangnan Hu - 通讯作者:
Jiangnan Hu
Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction
将非最大似然学习目标与最小 KL 收缩统一起来
- DOI:
- 发表时间:
2011 - 期刊:
- 影响因子:0
- 作者:
Siwei Lyu - 通讯作者:
Siwei Lyu
Siwei Lyu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 }}
{{ truncateString('Siwei Lyu', 18)}}的其他基金
SaTC: CORE: Small: Combating AI Synthesized Media Beyond Detection
SaTC:核心:小型:对抗无法检测的人工智能合成媒体
- 批准号:
2153112 - 财政年份:2022
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
NSF Convergence Accelerator Track F: Online Deception Awareness and Resilience Training (DART)
NSF 融合加速器轨道 F:在线欺骗意识和弹性培训 (DART)
- 批准号:
2230494 - 财政年份:2022
- 资助金额:
$ 45万 - 项目类别:
Cooperative Agreement
NSF Convergence Accelerator Track F: A Disinformation Range to Improve User Awareness and Resilience to Online Disinformation
NSF 融合加速器轨道 F:提高用户对在线虚假信息的认识和抵御能力的虚假信息范围
- 批准号:
2137871 - 财政年份:2021
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
RI: Small: A Study of New Aggregate Losses for Machine Learning
RI:小:机器学习新总损失的研究
- 批准号:
2103450 - 财政年份:2020
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
NRI: Collaborative Research: A Dynamic Bayesian Approach to Real Time Estimation and Filtering in Grasp Acquisition and Other Contact Tasks (Continuation)
NRI:协作研究:抓取采集和其他接触任务中实时估计和过滤的动态贝叶斯方法(续)
- 批准号:
1537257 - 财政年份:2015
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Blind Noise Estimation Using Signal Statistics in Random Band-Pass Domains
使用随机带通域中的信号统计进行盲噪声估计
- 批准号:
1319800 - 财政年份:2013
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
NRI-Small: Collaborative Research: A Dynamic Bayesian Approach to Real-Time Estimation and Filtering in Grasp Acquisition and Other Contact Tasks
NRI-Small:协作研究:在抓取采集和其他接触任务中进行实时估计和过滤的动态贝叶斯方法
- 批准号:
1208463 - 财政年份:2012
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
CAREER: A New Statistical Framework for Natural Images with Applications in Vision
职业:一种新的自然图像统计框架及其在视觉中的应用
- 批准号:
0953373 - 财政年份:2010
- 资助金额:
$ 45万 - 项目类别:
Continuing Grant
相似国自然基金
昼夜节律性small RNA在血斑形成时间推断中的法医学应用研究
- 批准号:
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
tRNA-derived small RNA上调YBX1/CCL5通路参与硼替佐米诱导慢性疼痛的机制研究
- 批准号:n/a
- 批准年份:2022
- 资助金额:10.0 万元
- 项目类别:省市级项目
Small RNA调控I-F型CRISPR-Cas适应性免疫性的应答及分子机制
- 批准号:32000033
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
Small RNAs调控解淀粉芽胞杆菌FZB42生防功能的机制研究
- 批准号:31972324
- 批准年份:2019
- 资助金额:58.0 万元
- 项目类别:面上项目
变异链球菌small RNAs连接LuxS密度感应与生物膜形成的机制研究
- 批准号:81900988
- 批准年份:2019
- 资助金额:21.0 万元
- 项目类别:青年科学基金项目
基于small RNA 测序技术解析鸽分泌鸽乳的分子机制
- 批准号:31802058
- 批准年份:2018
- 资助金额:26.0 万元
- 项目类别:青年科学基金项目
肠道细菌关键small RNAs在克罗恩病发生发展中的功能和作用机制
- 批准号:31870821
- 批准年份:2018
- 资助金额:56.0 万元
- 项目类别:面上项目
Small RNA介导的DNA甲基化调控的水稻草矮病毒致病机制
- 批准号:31772128
- 批准年份:2017
- 资助金额:60.0 万元
- 项目类别:面上项目
基于small RNA-seq的针灸治疗桥本甲状腺炎的免疫调控机制研究
- 批准号:81704176
- 批准年份:2017
- 资助金额:20.0 万元
- 项目类别:青年科学基金项目
水稻OsSGS3与OsHEN1调控small RNAs合成及其对抗病性的调节
- 批准号:91640114
- 批准年份:2016
- 资助金额:85.0 万元
- 项目类别:重大研究计划
相似海外基金
Phase Ib/II study of safety and efficacy of EZH2 inhibitor, tazemetostat, and PD-1 blockade for treatment of advanced non-small cell lung cancer
EZH2 抑制剂、他泽美司他和 PD-1 阻断治疗晚期非小细胞肺癌的安全性和有效性的 Ib/II 期研究
- 批准号:
10481965 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
SaTC: CORE: Small: Study, Detection and Containment of Influence Campaigns
SaTC:核心:小型:影响力活动的研究、检测和遏制
- 批准号:
2321649 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Exploring Sustainable Local Livelihood in the Digital Era: A Case Study of Small-Scale Shrimp Farmers in the Mekong Delta, Vietnam
探索数字时代可持续的当地生计:越南湄公河三角洲小规模虾农案例研究
- 批准号:
23KJ1260 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Grant-in-Aid for JSPS Fellows
Ancillary SOURCE Study: Characterization of Small Airway Basal Cell Biology in Early COPD
辅助来源研究:早期 COPD 中小气道基底细胞生物学的特征
- 批准号:
10736644 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
HCC: Small: Investigating the temporal dynamics of resilience during human-computer interaction: an EEG-fNIRS study
HCC:小:研究人机交互过程中弹性的时间动态:一项 EEG-fNIRS 研究
- 批准号:
2232869 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Study of teaching materials for programming education for elementary and junior high school students using small humanoid robots
小型仿人机器人中小学生编程教育教材研究
- 批准号:
23K02768 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
EAGER: Evaluation and implementation of a newly developed olfactometer for the study of sensory ecology in small marine organisms
EAGER:评估和实施新开发的嗅觉计,用于研究小型海洋生物的感官生态学
- 批准号:
2310259 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
A Prospective Cohort Study of Patients with Non-Small Cell Lung Cancer and Multiple Myeloma to Assess the Benefits and Harms Related to Cannabis Use During Treatment
对非小细胞肺癌和多发性骨髓瘤患者进行的前瞻性队列研究,以评估治疗期间使用大麻的益处和危害
- 批准号:
10792363 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Anthropological Study on Small Polities in South Sudan
南苏丹小政体的人类学研究
- 批准号:
23K12342 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
The Study of the paradox for multi-stage to the integration and small-size to big-size of wholesaler
批发商多级到一体化、小到大的悖论研究
- 批准号:
22K01777 - 财政年份:2022
- 资助金额:
$ 45万 - 项目类别:
Grant-in-Aid for Scientific Research (C)