基本信息
浏览量:43
职业迁徙
个人简介
Hi! I am a sixth-year graduate student in Computer Science at Stanford University. I am fortunate to be advised by Ashish Goel and Greg Valiant. My research interests lie in machine learning and algorithms, broadly including topics such as non-convex optimization, matrix and tensor factorizations, neural networks and its theory, and social network analysis.
At Stanford I often interact with the Theory Group, StatsML Group and Social Algorithms Lab. I received my Bachelor's degree from Prof. Yong Yu's ACM Honored Class in CS at Shanghai Jiao Tong University.
The goal of my work is developing meaningful theoretical insights and algorithms for real world applications. Thus far this has led to two lines of work:
Understanding the generalization of non-convex methods: Non-convex methods are the method of choice for training most ML models in practice. How much data is needed to train a model that generalizes well to unseen data?
Algorithms for social networks and their analysis beyond the worst-case: Dealing with large-scale social network data requires methods that scale to tens of millions of users. In the meantime, real world social networks admit structural properties. How do we exploit their structures to provide better algorithms and guarantees?
At Stanford I often interact with the Theory Group, StatsML Group and Social Algorithms Lab. I received my Bachelor's degree from Prof. Yong Yu's ACM Honored Class in CS at Shanghai Jiao Tong University.
The goal of my work is developing meaningful theoretical insights and algorithms for real world applications. Thus far this has led to two lines of work:
Understanding the generalization of non-convex methods: Non-convex methods are the method of choice for training most ML models in practice. How much data is needed to train a model that generalizes well to unseen data?
Algorithms for social networks and their analysis beyond the worst-case: Dealing with large-scale social network data requires methods that scale to tens of millions of users. In the meantime, real world social networks admit structural properties. How do we exploit their structures to provide better algorithms and guarantees?
研究兴趣
论文共 6 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
COLT 2018 (best paper); arXiv preprint arXiv:1712.09203 (2017)
引用97浏览0引用
97
0
KDD (2016): 1315-1324
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