基本信息
浏览量:255
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
个人简介
Research Theme:
All scientific and social disciplines are faced with an ever-increasing demand to analyze datasets that are unprecedented in scale (amount of data and its dimensionality) as well as degree of corruption (noise, outliers, missing and indirect observations). Extraction of meaningful information from such big and dirty datasets requires achieving the competing goals of computational efficiency and statistical optimality (optimal accuracy for a given amount of data). My research goal is to understand the fundamental tradeoffs between these two quantities, and design algorithms that can learn and leverage inherent structure of data in the form of clusters, graphs, subspaces and manifolds to achieve such tradeoffs.
Additionally, I am investigating how these tradeoffs can be further improved by designing interactive algorithms that employ judicious choice of where, what and how data is acquired, stored and processed. The vision is to introduce a new paradigm of intelligent machine learning algorithms that learn continually via feedback and make high-level decisions in collaboration with humans, thus pushing the envelope of automated scientific and social discoveries.
All scientific and social disciplines are faced with an ever-increasing demand to analyze datasets that are unprecedented in scale (amount of data and its dimensionality) as well as degree of corruption (noise, outliers, missing and indirect observations). Extraction of meaningful information from such big and dirty datasets requires achieving the competing goals of computational efficiency and statistical optimality (optimal accuracy for a given amount of data). My research goal is to understand the fundamental tradeoffs between these two quantities, and design algorithms that can learn and leverage inherent structure of data in the form of clusters, graphs, subspaces and manifolds to achieve such tradeoffs.
Additionally, I am investigating how these tradeoffs can be further improved by designing interactive algorithms that employ judicious choice of where, what and how data is acquired, stored and processed. The vision is to introduce a new paradigm of intelligent machine learning algorithms that learn continually via feedback and make high-level decisions in collaboration with humans, thus pushing the envelope of automated scientific and social discoveries.
研究兴趣
论文共 390 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
AAAI Spring Symposiano. 1 (2024): 572-572
CoRR (2023)
引用0浏览0EI引用
0
0
PLOS ONEno. 7 (2023): e0287443-e0287443
CoRR (2023): 4963-4985
引用0浏览0EI引用
0
0
arxiv(2023)
arxiv(2022)
J Mach Learn Res (2022): 225:1-225:48
引用0浏览0EI引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn