Research

Research Interests

My current interests include

• Optimization and Game Theory

• Machine Learning

• Optimal Transport

• Economic and Social Networks

Preprints

1. A nonasymptotic analysis of gradient descent ascent for nonconvex-concave minimax problems
   Tianyi Lin, Chi Jin and Michael I. Jordan.
   Revision. [SSRN]

2. Explicit second-order min-max optimization methods with optimal convergence guarantee
   Tianyi Lin, Panayotis Mertikopoulos and Michael. I. Jordan.
   Revision. [ArXiv]

3. Curvature-independent last-iterate convergence for games on Riemannian manifolds
   Yang Cai, Michael I. Jordan, Tianyi Lin, Argyris Oikonomou and Emmanouil-Vasileios Vlatakis-Gkaragkounis.
   Submitted. [ArXiv]

Selected Refereed Journal Publications

1. Perseus: A simple and optimal high-order method for variational inequalities
   Tianyi Lin and Michael I. Jordan.
   Mathematical Programming, 2024.
   [ArXiv] [DOI]

2. Doubly optimal no-regret online learning in strongly monotone games with bandit feedback
   Wenjia Ba, Tianyi Lin, Jiawei Zhang and Zhengyuan Zhou.
   Operations Research, 2024.
   [ArXiv] [SSRN] [DOI]

3. Monotone inclusions, acceleration and closed-loop control
   Tianyi Lin and Michael I. Jordan.
   Mathematics of Operations Research, 48(4): 2353-2382, 2023.
   [ArXiv] [DOI]

4. A control-theoretic perspective on optimal high-order optimization
   Tianyi Lin and Michael I. Jordan.
   Mathematical Programming, 195(1): 929-975, 2022.
   [ArXiv] [DOI]

5. On the efficiency of entropic regularized algorithms for optimal transport
   Tianyi Lin, Nhat Ho and Michael I. Jordan.
   Journal of Machine Learning Research, 23(137): 1-42, 2022.
   [ArXiv] [DOI]

6. A unified adaptive tensor approximation scheme to accelerate composite convex optimization
   Bo Jiang, Tianyi Lin and Shuzhong Zhang.
   SIAM Journal on Optimization, 30(4): 2897-2926, 2020.
   [ArXiv] [DOI]

7. On the global linear convergence of the ADMM with multi-block variables
   Tianyi Lin, Shiqian Ma and Shuzhong Zhang.
   SIAM Journal on Optimization, 25(3): 1478-1497, 2015.
   [ArXiv] [DOI]

Selected Refereed Conference Proceedings

1. Deterministic nonsmooth nonconvex optimization
   Michael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir and Manolis Zampetakis.
   Conference on Learning Theory (COLT), 2023.
   [ArXiv] [Earlier ArXiv] [DOI]

2. Gradient-free methods for deterministic and stochastic nonsmooth nonconvex optimization
   Tianyi Lin, Zeyu Zheng and Michael I. Jordan.
   Neural Information Processing Systems (NeurIPS), 2022.
   [ArXiv] [DOI]

3. First-order algorithms for min-max optimization in geodesic metric spaces
   Michael I. Jordan, Tianyi Lin and Emmanouil-Vasileios Vlatakis-Gkaragkounis.
   (Oral) Neural Information Processing Systems (NeurIPS), 2022.
   [ArXiv] [DOI]

4. Projection robust Wasserstein distance and Riemannian optimization
   Tianyi Lin*, Chenyou Fan*, Nhat Ho, Macro Cuturi and Michael I. Jordan.
   (Spotlight) Neural Information Processing Systems (NeurIPS), 2020.
   [ArXiv] [DOI]

5. Fixed-support Wasserstein barycenters: Computational hardness and fast algorithm
   Tianyi Lin, Nhat Ho, Xi Chen, Macro Cuturi and Michael I. Jordan.
   Neural Information Processing Systems (NeurIPS), 2020.
   [ArXiv] [DOI]

6. Finite-time last-iterate convergence for multi-agent learning in games
   Tianyi Lin*, Zhengyuan Zhou*, Panayotis Mertikopoulos and Michael I. Jordan.
   International Conference on Machine Learning (ICML), 2020.
   [ArXiv] [DOI]

7. On gradient descent ascent for nonconvex-concave minimax problems
   Tianyi Lin, Chi Jin and Michael I. Jordan.
   International Conference on Machine Learning (ICML), 2020.
   [ArXiv] [DOI]

8. Near-optimal algorithms for minimax optimization
   Tianyi Lin, Chi Jin and Michael I. Jordan.
   Conference on Learning Theory (COLT), 2020.
   [ArXiv] [DOI]

9. On efficient optimal transport: An analysis of greedy and accelerated mirror descent algorithms
   Tianyi Lin*, Nhat Ho* and Michael I. Jordan.
   International Conference on Machine Learning (ICML), 2019.
   [ArXiv] [DOI]

10. The dual-sparse topic model: Mining focused topics and focused terms in short text
    Tianyi Lin*, Wentao Tian*, Qiaozhu Mei and Hong Cheng.
    ACM International Conference on World Wide Web (WWW), 2014.
    [DOI]