(Algorithms, Data, Learning)
[About] [Members] [Gallary]
Our group is affiliated with
Institute for Interdisciplinary Information Sciences
(IIIS, previously ITCS), Tsinghua University. Generally speaking, our
members are interested in algorithms in a broad sense (including combinatorial
algorithms, geometric algorithms, graph theoretic algorithms, as well as
algorithms in databases, and machine learning). We like to design new algorithms
which have nice theoretical guarantees and perform well in practice. In
particular, we have the following research directions:
- Theoretical Computer Science
(mainly algorithms, including approximation algorithms, hardness of
approximation, algorithmic game theory, computational geometry,
string algorithms, stochastic optimization)
- Big data analytics (traffic
data analysis, spatial-temporal databases, crowdsourcing)
- Machine Learning (efficient
ML algorithms, deep learning, learning theory, online learning,
applications to Finance)
- Congratulations to Dr. Lingxiao Huang, Mengwen Xu and
Dong Wang for successfully defending their Phd thesis!
- A new ICML paper: Learning Gradient Descent: Better
Generalization and Longer Horizons. Kaifeng Lv, Shunhua Jiang, Jian Li. The
34th International Conference on Machine Learning (ICML 2017)
- Two COLT papers got accepted : Nearly Optimal
Sampling Algorithms for Combinatorial Pure Exploration. Lijie Chen, Anupam
Gupta, Jian Li, Mingda Qiao, Ruosong Wang.; Towards Instance Optimal Bounds
for Best Arm Identification. Lijie Chen, Jian Li, Mingda Qiao.
- Our new paper k-Regret Minimizing Set: Efficient
Algorithms and Hardness. Wei Cao, Jian Li, Haitao Wang, Kangning Wang,
Ruosong Wang, Raymond Chi-Wing Wong and Wei Zhan. got the
ICDT 2017 best
- Our new paper (Lingxiao Huang and Jian Li) Stochastic
k-Center and j-Flat-Center Problems is accepted to SODA17.
- The new paper Combinatorial Multi-Armed Bandit with
General Reward Functions (Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan
Lu) is accepted to NIPS16.
- Congratulations to Wei Cao and Dong Wang: their team
won the 2nd place (out of 1650 teams all over the world) in the Didi demand
- Our new paper DESTPRE : A Data-Driven Approach to
Destination Prediction for Taxi Rides (Mengwen Xu, Dong Wang, Jian Li) is
accepted to UbiComp 2016.
- Our new paper epsilon-Kernel Coresets for Stochastic
Points. (Lingxiao Huang, Jian Li, Jeff Phillips and Haitao Wang. ) is
accepted to the 24rd Annual European Symposium on Algorithms (ESA16).
- Almost All Even Yao-Yao Graphs Are Spanners. (Jian
Li, Wei Zhan) is accepted to the 24rd Annual European Symposium on
Algorithms (ESA 2016).
- Kai Jin has successfully defended his Ph.D. thesis!
- Our new paper K-Means Clustering with Distributed
Dimension (Hu Ding, Yu Liu, Lingxiao Huang, Jian Li) is accepted to
International Conference on Machine Learning (ICML16).
We provide a communication efficient approximation
algorithm for k-means clustering in distributed setting.
- Our new paper Pure Exploration of Multi-armed
Bandit Under Matroid Constraints. (Lijie Chen, Anupum Gupta, Jian Li)
is accepted to Conference on Learning Theory (COLT 2016).
- Canonical Paths for MCMC: from Art to Science.
(Lingxiao Huang, Pinyan Lu and Chihao Zhang), is accepted to SODA 2016.
- Our paper Automatic User Identification Method
across Heterogeneous Mobility Data Souces (Wei Cao, Zhengwei Wu, Jian Li,
Haishan Wu) is accepted to ICDE16. We provide a very
efficient map-reduce based algorithm for identifying the same users from
different trajectory databases.
- Our new paper On Top-k Selection in Multi-Armed
Bandits and Hidden Bipartite Graphs. (Wei Cao, Jian Li, Yufei Tao, Zhize Li)
is accepted to Neural Information Processing Systems (NIPS), 2015.
- Our paper A PTAS for the Weighted Unit Disk Cover
Problem (Jian Li, Yifei Jin) is published in the 42nd International
Colloquium on Automata, Languages, and Programming (ICALP 2015).
In this paper, we provide the first PTAS for the weighted unit disk cover
problem, which settles an open question raised in a number of previous
- Our paper Learning Arbitrary Statistical Mixtures
of Discrete Distributions. (Jian Li, Yuval Rabani, Leonard J. Schulman,
Chaitanya Swamy) is published in ACM Symposium on the Theory of Computing
(STOC 2015). We provide the first efficient
algorithms for learning the mixture of general discrete distributions
without making any restricting assumptions on the structure of the
2016 Spring, ATCS
Prediction - theory and practice (graduate)