Zhize Li (李志泽)        

I am now a postdoc at King Abdullah University of Science and Technology (KAUST) advised by Prof. Peter Richtárik.

I received my Ph.D. degree in July 2019 from the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University. My Advisor was Prof. Jian Li.

I was a visiting scholar at Computer Science Department of Duke University (Hosted by Prof. Rong Ge) and a visiting scholar at Industrial and Systems Engineering (ISyE) of Georgia Institute of Technology (Hosted by Prof. Guanghui (George) Lan).

My research interests lie in theoretical computer science and machine learning, in particular (non-)convex optimization algorithms, machine learning, algorithms and data structures.

PhD thesis: Simple and Fast Optimization Methods for Machine Learning. June 2019.
2019 Tsinghua Outstanding Doctoral Dissertation Award.

Publications (by date) [by topic] [google scholar]

1. A Unified Variance-Reduced Accelerated Gradient Method for Convex Optimization

   Guanghui Lan, Zhize Li, Yi Zhou (alphabetical order)

   33rd Conference on Neural Information Processing Systems (NeurIPS 2019)

2. SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points

   Zhize Li

   33rd Conference on Neural Information Processing Systems (NeurIPS 2019)

3. A Fast Anderson-Chebyshev Mixing Method for Nonlinear Optimization

   Zhize Li, Jian Li. Manuscript.

4. Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

   Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu, Jian Li

   (Machine Learning), 2019, journal.

5. Gradient Boosting With Piece-Wise Linear Regression Trees

   Yu Shi, Jian Li, Zhize Li

   28th International Joint Conference on Artificial Intelligence (IJCAI 2019)

6. Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization

   Rong Ge, Zhize Li, Weiyao Wang, Xiang Wang (alphabetical order)

   32nd Annual Conference on Learning Theory (COLT 2019)

7. Learning Two-layer Neural Networks with Symmetric Inputs

   Rong Ge, Rohith Kuditipudi, Zhize Li, Xiang Wang (alphabetical order)

   7th International Conference on Learning Representations (ICLR 2019)

8. A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization

   Zhize Li, Jian Li

   32nd Conference on Neural Information Processing Systems (NeurIPS 2018). (spotlight)

9. Optimal In-Place Suffix Sorting

   Zhize Li, Jian Li, Hongwei Huo

   25th International Symposium on String Processing and Information Retrieval (SPIRE 2018). (invited) [long paper] [slides] [full version in arXiv] submitted to journal.

   Previous one-page [summary paper] appeared in 28th IEEE Data Compression Conference (DCC 2018)

   We give the first in-place suffix array (a fundamental data structure in string processing and data compression, as a space-efficient alternative to suffix tree) construction algorithm which is optimal both in time and space. In particular, our algorithm solves the important open problem posed by Franceschini and Muthukrishnan in ICALP 2007. Unfortunately, our paper has been prevented from being published since 2017 due to a malicious conflict of interest [a disclaimer].

10. A Fast Polynomial-time Primal-Dual Projection Algorithm for Linear Programming

    Zhize Li, Wei Zhang, Kees Roos

    23rd International Symposium on Mathematical Programming (ISMP 2018) [full version] in submission

11. Optimal Two-Stage Mechanism for Ordinal Peer Assessment

    Zhize Li, Le Zhang, Zhixuan Fang, Jian Li

    11th International Symposium on Algorithmic Game Theory (SAGT 2018)

12. On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs

    Wei Cao, Jian Li, Yufei Tao, Zhize Li

    28th Conference on Neural Information Processing Systems (NIPS/NeurIPS 2015)

Experience/Services

• Conference reviewer: AAAI 2020 (PC), NeurIPS 2019, ECML 2019, COLT 2019, ICML 2019, STOC 2019, COLT 2018, ICML 2017, AAAI 2017, ICALP 2016.

• Journal reviewer: Computational Optimization and Applications (COAP), Journal of Machine Learning Research (JMLR), IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Parallel and Distributed Systems (TPDS), IEEE/ACM Transactions on Networking (ToN).

• Research Assistant (RA):

    Tsinghua-MIT-CUHK Research Center for Theoretical Computer Science (Sep, 2014 - Jun, 2019)

• Teaching Assistant (TA):

  1. Advanced Theoretical Computer Science for graduate students (2017 Spring)
  2. Algorithm Design for undergraduate students (Yao Class) (2015 Fall)

• The 2016 National Combinatorial Optimization Summer School

    Courses: Computational Complexity, Approximation Algorithms, Randomized Algorithms

    Outstanding Student (top 10/110)

• Algorithm Engineer Intern: Alibaba (Jul - Aug, 2013), NetEase (Jun - Aug, 2017)

Invited Talks/Posters

1. China Theory Week 2018 (founded by Prof. Andrew Chi-Chih Yao in 2007) [slides]
2. The 16th China Symposium on Machine Learning and Applications (MLA'18) [slides] [poster]

Conference Talks/Posters

NeurIPS 2018, SPIRE 2018, SAGT 2018, ISMP 2018, DCC 2018, NIPS 2015.

Selected Awards

• National Scholarship (top 1%)
• Pacesetter of Outstanding Graduates (highest)
• The First Prize in Collegiate Advanced Mathematics Contest (highest)

Contact

Zhize Li

Email: zhizeli DOT thu AT gmail DOT com

zz-li14 AT mails DOT tsinghua DOT edu DOT cn

Address: Room 4-609, FIT Building, Tsinghua University, Beijing 100084, China