Qiujiang Jin
About me
I graduated with my Ph.D. degree from the Department of Electrical and Computer Engineering of University of Texas at Austin. I was a member of the Wireless Networking and Communications Group and I was advised by Prof. Aryan Mokhtari. I received my B.Sc. in pure and applied mathematics from the Department of Mathematical Sciences at Tsinghua University and my M.Sc. in computational and mathematical engineering from the Institute for Computational & Mathematical Engineering at Stanford University. My research interests generally lie in the theory and applications of optimization. My current research focuses on the development of efficient second-order numerical optimization methods for large-scale machine learning problems.
Publications and Preprints
[Non-asymptotic Superlinear Convergence of Standard Quasi-Newton Methods] Qiujiang Jin and Aryan Mokhtari Mathematical Programming, 1-49, 2022.
[Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach] Qiujiang Jin and Aryan Mokhtari Advances in Neural Information Processing Systems (NeurIPS), 2021.
[Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood] Qiujiang Jin, Alec Koppel, Ketan Rajawat and Aryan Mokhtari International Conference on Machine Learning (ICML), 2022.
[Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear Convergence] Ruichen Jiang, Qiujiang Jin and Aryan Mokhtari Conference on Learning Theory (COLT), 2023.
[Statistical and Computational Complexities of BFGS Quasi-Newton Method for Generalized Linear Models] Qiujiang Jin, Tongzheng Ren, Nhat Ho and Aryan Mokhtari Transactions on Machine Learning Research, 2024.
[Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search] Qiujiang Jin, Ruichen Jiang and Aryan Mokhtari Advances in Neural Information Processing Systems (NeurIPS), 2024. (Spotlight)
[Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization] Ruichen Jiang, Ali Kavis, Qiujiang Jin, Sujay Sanghavi and Aryan Mokhtari Advances in Neural Information Processing Systems (NeurIPS), 2024.
[Non-asymptotic Global Convergence Rates of BFGS with Exact Line Search] Qiujiang Jin, Ruichen Jiang and Aryan Mokhtari Mathematical Programming, 2025.
[Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance] Qiujiang Jin and Aryan Mokhtari Under Review, 2025
|