Wei Hu

Wei Hu 

Wei Hu (胡威)
Ph.D. Student
Department of Computer Science
Princeton University

Email: huwei [at] cs (dot) princeton (dot) edu

About

I am a first-year PhD student in the Department of Computer Science at Princeton University. I am very fortunate to be advised by Sanjeev Arora. Previously, I did my undergrad at Tsinghua University, where I was a member of Yao Class.

My primary research interests are in the intersection of theoretical computer science and machine learning. In particular, I am interested in designing practical and provable algorithms for machine learning and optimization problems.

Publications

(* indicates alphabetical order)

Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls [arxiv]

* Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li
Manuscript, 2017

Combinatorial Multi-Armed Bandit with General Reward functions [arxiv]

* Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu
In Conference on Neural Information Processing Systems (NIPS), 2016

New Characterizations in Turnstile Streams with Applications [paper] [slides]

* Yuqing Ai, Wei Hu, Yi Li, David P. Woodruff
In Computational Complexity Conference (CCC), 2016

WarpMap: Accurate and Efficient Indoor Location by Dynamic Warping in Sequence-Type Radio-Map [paper]

Xuehan Ye, Yongcai Wang, Wei Hu, Lei Song, Zhaoquan Gu, Deying Li
In IEEE International Conference on Sensing, Communication and Networking (SECON), 2016

Sequence-Type Fingerprinting for Indoor Localization [paper]

Wei Hu, Yongcai Wang, Lei Song
In International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2015

Talks

New Characterizations in Turnstile Streams with Applications

Computational Complexity Conference (CCC), May 2016, Tokyo, Japan

Combinatorial Multi-Armed Bandit with General Reward Functions

MSR Asia Theory Group Seminar, March 2016, Beijing, China

Selected Awards