Tao Sun (孙涛)
About me
I am now an associate professor in a research group led by Prof. Xinwang Liu.
News
Starting in September 2024, I will update the news section to collect the rejection experiences from my academic journey.
2024-11 One paper was rejected by NC.
2024-10 Two papers were rejected by AAAI in the first round.
2024-9 One paper was rejected by NeurIPS, and another paper was withdrawn before. As a wise person once said, "As long as the withdrawal is done quickly, it won't be rejected." (no reference)
Education
Ph.D., Computational Mathematics, National University of Defense Technology, 12.2018
M.S., Computational Mathematics, National University of Defense Technology, 12.2014
B.S., Applied Mathematics, National University of Defense Technology, 06.2012
Experience
Associate professor, National University of Defense Technology, 12.2022--Now
Assistant professor, National University of Defense Technology, 03.2019--12.2022
Research
My research interests include:
Machine Learning
Deep Learning
Optimization
Distributed Learning
Selected Conference Papers
X. Deng**, T. Sun*, S. Li, D. Li*, X. Lu, "Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness.", NeurIPS, 2024.
X. Pan, X. Li, J. Liu, T. Sun, K. Sun, L. Chen, Z. Qu, "Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-) Convex One to K-Level Stochastic Optimizations.", ICML, 2024.
X. Deng**, T. Sun*, D. Li*, X. Lu, "Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1.", IJCAI, 2024.
T. Sun, Q. Wang, D. Li, B. Wang, "Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions.", ICML, 2023.
X. Deng**, T. Sun*, S. Li, D. Li*, "Stability-Based Generalization Analysis of the Asynchronous Decentralized SGD.", AAAI, 2023.
T. Sun, D. Li, B. Wang, "Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks." Advances in Neural Information Processing Systems, 2022.
T. Sun, D. Li, B. Wang, "Adaptive Random Walk Gradient Descent for Decentralized Optimization." International Conference on Machine Learning, 2022.
T. Sun, D. Li, B. Wang, "Stability and Generalization of the Decentralized Stochastic Gradient Descent." Proceedings of the AAAI Conference on Artificial Intelligence 35, pp. 9756-9764 2021.
T. Sun, D. Li, Z. Quan, H. Jiang, S. Li, Y. Dou, "Heavy-ball Algorithms Always Escape Saddle Points". Proceedings of the International Joint Conference on Artificial Intelligence, pp.3520-3526, 2019.
T. Sun, P. Yin, D. Li, C. Huang, L. Guan, H. Jiang, "Non-ergodic Convergence Analysis of Heavy-ball Algorithms." Proceedings of the AAAI Conference on Artificial Intelligence 33, pp. 5033-5040, 2019.
T. Sun, Y. Sun, D. Li, Q. Liao, "General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme", Advances in Neural Information Processing Systems 32, 2019.
T. Chen, G. Giannakis, T. Sun, W. Yin, "LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning.", Advances in Neural Information Processing Systems 31, 2018.
T. Sun, Y. Sun, W. Yin, "On Markov Chain Gradient Descent", Advances in Neural Information Processing Systems 31, 2018.
T. Sun, R. Hannah, W. Yin, "Asynchronous Coordinate Descent under More Realistic Assumptions", Advances in Neural Information Processing Systems 30, 2017.
Selected Journal Papers
S. Chen, X. Deng**, D. Xu*, T. Sun*, D. Li, "Decentralized stochastic sharpness-aware minimization algorithm", Neural Networks Journal, 2024.
T. Sun, Q. Wang, Y. Lei, D. Li, and B. Wang, "Pairwise Learning with Adaptive Online Gradient Descent", Transactions on Machine Learning Research, 2023.
T. Sun, D. Li, B. Wang, "On the Decentralized Stochastic Gradient Descent with Markov Chain Sampling", IEEE Transactions on Signal Processing , 2023.
T. Sun, D. Li, B. Wang, "Decentralized Federated Averaging.", IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022.
T. Sun, D. Li, "General Nonconvex Total Variation and Low-Rank Regularizations: Model, Algorithm and Applications.", Pattern Recognition Journal , 2022.
T. Sun, D. Li, "Sign Stochastic Gradient Descents without Bounded Gradient Assumption for the Finite Sum Minimization.", Neural Networks Journal , 2022.
B. Wang#, T. M. Nguyen#, T. Sun#, A. L. Bertozzi, R. G. Baraniuk, S. J. Osher, "Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent.", SIAM J. Imaging Sciences , 2021.
T. Sun, H. Shen, T. Chen, D. Li, "Adaptive Temporal Difference Learning with Linear Function Approximation.", IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021.
T. Sun, L. Qiao, Q. Liao, D. Li, "Novel Convergence Results of Adaptive Stochastic Gradient Descent.", IEEE Transactions on Image Processing, 2020.
T. Sun, L. Qiao, D. Li, "Non-ergodic Complexity of Proximal Inertial Gradient Descents.", IEEE Transactions on Neural Networks and Learning Systems, 2020.
T. Sun, K. Tang, D. Li, "Gradient Descent Learning with Floats.", IEEE Transactions on Cybernetics, 2020.
T. Sun, D. Li, "Capri: Consensus Accelerated Proximal Reweighted Iteration for A Class of Nonconvex Minimizations.", IEEE Transactions on Knowledge and Data Engineering, 2020.
T. Sun, Y. Sun, Y. Xu, W. Yin, "Markov Chain Block Coordinate Descent.", Computational Optimization and Applications, pp. 35-61, 2020.
T. Sun, R. Barrio, M. Rodriguez, H. Jiang, "Inertial Nonconvex Alternating Minimizations for the Image Deblurring.", IEEE Transactions on Image Processing, pp. 6211-6224, 2019.
T. Sun, P. Yin, H. Jiang, W. Zhu, "Iteratively Linearized Reweighted Alternating Direction Method of Multipliers for A Class of Nonconvex Problems.", IEEE Transactions on Signal Processing, pp.5380-5391, 2018.
T. Sun, P. Yin, H. Jiang, L. Cheng, "Alternating Direction Method of Multipliers with Difference of Convex Functions.", Advances in Computational Mathematics, pp.723-744, 2018.
T. Sun, H. Jiang, L. Cheng, "Convergence of Proximal Iteratively Reweighted Nuclear Norm Algorithm for Image Processing.", IEEE Transactions on Image Processing , pp. 5632-5644, 2017.
T. Sun, H. Jiang, L. Cheng, "Global Convergence of Proximal Iteratively Reweighted Algorithm", Journal of Global Optimization, pp. 815-826, 2017.
Note: *indicates the corresponding author, # denotes equal contributions,** denotes my student.
Full list of publications.
Academic service
Action Editors
Neural Networks, Elsevier(Starting From 2025)
Computational Intelligence, Wiley
Scientific Reports, Nature
Reviewer
NeurIPS, ICML, ICLR, ECML, TMLR, AAAI, IJCAI, TPAMI
Invited Talks
Others
Grants (Chinese)
Awards (Chinese)
CCF优博提名奖2020
ACM中国新星奖(长沙分会,排名第一),2023
国防科大青年科技创新奖2023
湖南省优秀博士论文奖2021
|