← Back to home

Preprints

  1. Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization. [arXiv]
    Wei Jiang, Rui Yan, Sifan Yang, Yuanyu Wan, Lijun Zhang, and Zechao Li
  2. Convergence Analysis of STORM Under Different Geometries. [arXiv]
    Wei Jiang, Yibo Wang, Wenhao Yang, Rui Yan, Lijun Zhang, and Zechao Li
  3. Revisiting Distributed Sign-Based Variance Reduction. [arXiv]
    Wei Jiang, Zechao Li, and Lijun Zhang
  4. Better Convergence Guarantees for Sign-Based Momentum Methods. [arXiv]
    Wei Jiang, Dingzhi Yu, Sifan Yang, Wenhao Yang, Zechao Li, and Lijun Zhang
  5. Non-Stationary Projection-Free Online Learning with Dynamic Regret Guarantees.
    Yibo Wang, Haomin Bai, Wei Jiang, Wenhao Yang, Yuanyu Wan, and Lijun Zhang
  6. Dual Adaptivity: Universal Algorithms for Minimizing the Adaptive Regret of Convex Functions. [arXiv]
    Lijun Zhang, Wenhao Yang, Guanghui Wang, Wei Jiang, and Zhi-Hua Zhou

Journal

  1. TPAMI 2026 Optimizing Unnormalized Statistical Models through Compositional Optimization [PDF]
    Wei Jiang, Jiayu Qin, Lingyu Wu, Changyou Chen, Tianbao Yang, and Lijun Zhang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 48(2): 1949 - 1960, 2026.
  2. TPAMI 2025 Revisiting Stochastic Multi-Level Compositional Optimization. [PDF]
    Wei Jiang, Sifan Yang, Yibo Wang, Tianbao Yang, and Lijun Zhang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 47(7): 5613 - 5624, 2025.
  3. Journal of Software 2025 Normalized Adaptive Variance Reduction Method. [PDF]
    Wei Jiang, Sifan Yang, Yibo Wang, and Lijun Zhang
    Journal of Software, 36(11): 4893 - 4905, 2025.

Conference

  1. ICML 2026 Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
    Wei Jiang, Mao Xu, Wenhao Yang, Yibo Wang, Zechao Li, and Lijun Zhang
    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), to appear, 2026.
  2. ICML 2026 Mirror Descent Under Generalized Smoothness [arXiv]
    Dingzhi Yu, Wei Jiang, Hongyi Tao, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), to appear, 2026.
  3. ICML 2026 Distributed Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower bounds [arXiv]
    Sifan Yang, Wenhao Yang, Wei Jiang, and Lijun Zhang
    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), to appear, 2026.
  4. IJCAI 2025 Smoothed Online Convex Optimization with Delayed Feedback [PDF]
    Sifan Yang, Wenhao Yang, Wei Jiang, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), pages 6812 - 6820, 2025.
  5. NeurIPS 2024 Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions [PDF]
    Wei Jiang, Sifan Yang, Yibo Wang, and Lijun Zhang
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 22047 - 22080, 2024.
  6. NeurIPS 2024 Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction [PDF]
    Wei Jiang, Sifan Yang, Wenhao Yang, and Lijun Zhang
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 33891 - 33932, 2024.
  7. NeurIPS 2024 Online Composite Optimization Between Stochastic and Adversarial Environments [PDF]
    Yibo Wang, Sijia Chen, Wei Jiang, Wenhao Yang, Yuanyu Wan, and Lijun Zhang
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 94808 - 94850, 2024.
  8. ICML 2024 Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization [PDF]
    Wei Jiang, Sifan Yang, Wenhao Yang, Yibo Wang, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 21962 - 21987, 2024.
  9. ICML 2024 Small-loss Adaptive Regret for Online Convex Optimization [PDF]
    Wenhao Yang, Wei Jiang, Yibo Wang, Ping Yang, Yao Hu, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 56156 - 56195, 2024.
  10. ICML 2024 Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond [PDF]
    Dingzhi Yu, Yunuo Cai, Wei Jiang, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 57384 - 57414, 2024.
  11. AAAI 2024 Non-stationary Projection-free Online Learning with Dynamic and Adaptive Regret Guarantees [PDF, arXiv]
    Yibo Wang, Wenhao Yang, Wei Jiang, Shiyin Lu, Bing Wang, Haihong Tang, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), pages 15671 - 15679, 2024.
  12. ICML 2023 Learning Unnormalized Statistical Models via Compositional Optimization [PDF]
    Wei Jiang, Jiayu Qin, Lingyu Wu, Changyou Chen, Tianbao Yang, and Lijun Zhang
    In Proceedings of the 40th International Conference on Machine Learning (ICML 2023), pages 15105 - 15124, 2023.
  13. NeurIPS 2022 Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [PDF, Supplementary]
    Wei Jiang, Gang Li, Yibo Wang, Lijun Zhang, and Tianbao Yang
    In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pages 32499 - 32511, 2022.
  14. NeurIPS 2022 Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor [PDF, Supplementary]
    Lijun Zhang, Wei Jiang, Jinfeng Yi, and Tianbao Yang
    In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pages 4928 - 4942, 2022.
  15. ICML 2022 Optimal Algorithms for Stochastic Multi-Level Compositional Optimization [PDF]
    Wei Jiang, Bokun Wang, Yibo Wang, Lijun Zhang, and Tianbao Yang
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022), pages 10195 - 10216, 2022.
  16. NeurIPS 2021 Revisiting Smoothed Online Learning [PDF, Supplementary]
    Lijun Zhang, Wei Jiang, Shiyin Lu, and Tianbao Yang
    In Advances in Neural Information Processing Systems 34 (NeurIPS 2021), pages 13599 - 13612, 2021.
  17. NeurIPS 2021 Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions [PDF, Supplementary]
    Lijun Zhang, Guanghui Wang, Wei-Wei Tu, Wei Jiang, and Zhi-Hua Zhou
    In Advances in Neural Information Processing Systems 34 (NeurIPS 2021), pages 24968 - 24980, 2021.