Publications

Preprints and Submitted

• Unifying Distributionally Robust Optimization via Optimal Transport Theory [arxiv]
  ($\alpha$-$\beta$ order) Jose Blanchet, Daniel Kuhn, Jiajin Li$^\star$, Bahar Taskesen.
  To be submitted to SIAM Journal on Optimization.

• Nonsmooth Nonconvex-Nonconcave Minimax Optimization: Primal-Dual Balancing and Iteration Complexity Analysis [arxiv]
  Jiajin Li, Linglingzhi Zhu, Anthony Man-Cho So.
  Under review at Mathematical Programming.
  Preliminary version accepted by NeurIPS 2022 Workshop on Optimization for Machine Learning (OPT 2022), Oral.

• Trade-off among Infeasibility, Efficiency and Accuracy for Gromov-Wasserstein Computation [arxiv]
  Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet.
  To be submitted to Journal of Machine Learning Research.

• Synthetic Principle Component Design: Fast Covariate Balancing with Synthetic Controls
  Yiping Lu, Jiajin Li, Lexing Ying, Jose Blanchet.
  NeurIPS 2022 Workshop on Causality for Real-world Impact.

Publication

• Doubly Smoothed GDA: Global Convergent Algorithm for Constrained Nonconvex-Nonconcave Minimax Optimization [arxiv]
  Taoli Zheng, Linglingzhi Zhu, Anthony Man-Cho So, Jose Blanchet, Jiajin Li$\star$.
  Neural Information Processing Systems (NeurIPS), 2023.
• Outlier-Robust Gromov Wasserstein for Graph Data [arxiv]
  Lemin Kong, Jiajin Li, Anthony Man-Cho So.
  Neural Information Processing Systems (NeurIPS), 2023. [Spotlight presentation.]
• A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data [paper]
  Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet.
  International Conference on Learning Representation (ICLR), 2023.
• Learning Proximal Operators to Discover Multiple Optima [arxiv]
  Lingxiao Li, Noam Aigerman, Vladimir G. Kim, Jiajin Li, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon.
  International Conference on Learning Representation (ICLR), 2023.
• Wasserstein Distributionally Robust Linear-Quadratic Estimation under Martingale Constraints [paper]
  Kyriakos Lotidis, Nicholas Bambos, Jose Blanchet, Jiajin Li.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
• Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport
  Jianheng Tang, Weiqi Zhang, Jiajin Li, Kangfei Zhao, Fugee Tsung, Jia Li.
  International Conference on Data Engineering (ICDE), 2023.
• A Splitting Scheme for Flip-Free Distortion Energies [paper] [project page]
  Oded Stein, Jiajin Li, Justin Solomon.
  SIAM Journal on Imaging Sciences (SIIMS), to appear.
• Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints [arxiv]
  Jiajin Li, Sirui Lin, Jose Blanchet, Viet Anh Nguyen.
  Neural Information Processing Systems (NeurIPS), 2022.
• Rethinking Graph Neural Networks for Anomaly Detection [paper] [code]
  Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li.
  International Conference on Machine Learning (ICML), 2022.
• Modified Frank Wolfe in Probability Space [paper] [code]
  Carson Kent, Jiajin Li, Jose Blanchet, Peter Glynn.
  Neural Information Processing Systems (NeurIPS), 2021.
• Deconvolutional Networks on Graph Data [paper] [code]
  Jia Li, Jiajin Li, Yang Liu, Jianwei Yu, Yueting Li, Hong Cheng.
  Neural Information Processing Systems (NeurIPS), 2021.
• Understanding Notions of Stationarity in Nonsmooth Optimization [paper]
  Jiajin Li, Anthony Man-Cho So, Wing-Kin Ma.
  IEEE Signal Processing Magazine (SPM), 2020.
• Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust SVM [paper] [code]
  Jiajin Li, Caihua Chen, Anthony Man-Cho So.
  Neural Information Processing Systems (NeurIPS), 2020.
• Dirichlet Graph Variational Autoencoder [paper] [code]
  Jia Li, Jianwei Yu, Jiajin Li, Honglei Zhang, Kangfei Zhao, Yu Rong, Hong Cheng, Junzhou Huang.
  Neural Information Processing Systems (NeurIPS), 2020.
• The Gambler’s Problem and Beyond [paper]
  Baoxiang Wang, Shuai Li, Jiajin Li, Siu on Chan.
  International Conference on Learning Representations (ICLR), 2020.
• A First-Order Algorithmic Framework for Distributionally Robust Logistic Regression [paper] [code]
  Jiajin Li, Sen Huang, Anthony Man-Cho So.
  Neural Information Processing Systems (NeurIPS), 2019.
• Policy Optimization with Second-Order Advantage Information [paper] [code]
  ($\alpha$-$\beta$ order) Jiajin Li, Baoxiang Wang.
  International Joint Conference on Artificial Intelligence (IJCAI), 2018.