Chengchang Liu (刘程畅)

alt text 

Chengchang Liu, Ph.D candidate@CUHK
Email: 7liuchengchang@gmail.com

About me

I am a Ph.D candidate under supervision of Prof. John C.S. Lui. I received a B.S. in Statistics from USTC at 2022.

Previously, I visited CUHK (SZ) in 2024, hosted by Prof. Zhi-Quan (Tom) Luo. I also work closely with Prof. Luo Luo.

My research focuses on designing efficient optimization methods for large-scale problems and the intersection of quantum computing and optimization.

I am the PI for the NSFC basic research scheme for PhD students on ‘‘Second-Order Optimization for Large-Scale Machine Learning: Algorithms and Analysis’’ from 2025 to 2026.

Publications

  1. Solving Convex-Concave Problems with Õ(ɛ^{-4/7}) Second-order Oracle Complexity.
    Lesi Chen, Chengchang Liu, Luo Luo, Jingzhao Zhang.
    COLT, 2025

  2. Second-order Min-Max Optimization with Lazy Hessians.
    Lesi Chen, Chengchang Liu, Jingzhao Zhang.
    ICLR, 2025 (oral)

  3. An Enhanced Levenberg–Marquardt Method via Gram Reduction.
    Chengchang Liu, Luo Luo, John C.S. Lui.
    AAAI, 2025

  4. Quantum Algorithms for Non-smooth Non-convex Optimization.
    Chengchang Liu, Chaowen Guan, Jianhao He, John C.S. Lui.
    NeurIPS, 2024

  5. Quantum Algorithm for Online Exp-concave Optimization.
    Jianhao He, Chengchang Liu, Xutong Liu, Lvzhou Li, John C.S. Lui.
    ICML, 2024

  6. Communication Efficient Distributed Newton Method over Unreliable Networks.
    Ming Wen, Chengchang Liu, Yuedong Xu.
    AAAI, 2024

  7. Communication Efficient Distributed Newton Method with Fast Convergence Rates.
    Chengchang Liu, Lesi Chen, Luo Luo, John C.S. Lui.
    KDD, 2023

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

  9. Quasi-Newton Methods for Saddle Point Problems.
    Chengchang Liu, Luo Luo.
    NeurIPS, 2022 (spotlight)

  10. 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)

Selected Preprints

  1. Computationally Faster Newton Methods by Lazy Evaluations.
    Lesi Chen, Chengchang Liu, Luo Luo, Jingzhao Zhang.
    arXiv preprint, 2025

  2. Symmetric Rank-k Methods.
    Chengchang Liu, Cheng Chen, Luo Luo.
    arXiv preprint, 2023

Services

  • Conference Reviewer: NeurIPS 2023-25, ICLR 2024-25, AISTATS 2024, ICML 2024-25, AAAI 2025.