Chengchang Liu (刘程畅)

Chengchang Liu Department of Computer Science and Engineering The Chinese University of Hong Kong Contact: 7liuchengchang@gmail.com

About me

I received a B.S in statistics from the University of Science and Technology of China (USTC) in 2022.

I am interesed in optimization. I am always open for possible collaborations. Please feel free to contact me.

Research

My recent research focus on designing efficient methods (especially second-order methods) for large-scale optimization problems with strong theoretical guarantees.

Email me if you have any questions about my works.

Selected Works

1. Symmetric Rank-k Methods.
   Chengchang Liu, Cheng Chen, Luo Luo.
   Prepared in 2023
   [pdf]

2. Block Broyden's Methods for Solving Nonlinear Equations.
   Chengchang Liu, Cheng Chen, Luo Luo, John C.S. Lui.
   NeurIPS 2023
   [pdf]

3. Communication Efficient Distributed Newton Method with Fast Convergence Rates.
   Chengchang Liu, Lesi Chen, Luo Luo, John C.S. Lui.
   KDD 2023
   [pdf] [code]

4. Regularized Newton Methods for Variational Inequalities with Hölder Continuous Jacobians.
   Chengchang Liu, Luo Luo.
   Prepared in 2022
   [pdf]

5. Quasi-Newton Methods for Saddle Point Problems.
   Chengchang Liu, Luo Luo.
   NeurIPS 2022 Spotlight
   [pdf] [code] [Longer Version]
   

6. Partial-Quasi-Newton Methods: Efficient Algorithms for Minimax Optimization Problems with Unbalanced Dimensionality.
   Chengchang Liu, Shuxian Bi, Luo Luo, John C.S. Lui.
   KDD 2022 Best Paper Runner-Up
   [pdf] [code]
   

Services

• Conference Reviewer: NeurIPS 2023, ICLR 2024, AISTATS 2024.