Tianyuan Jin

Research Fellow Department of Electrical and Computer Engineering National University of Singapore

Bio

I am a Research Fellow at the Department of Electrical and Computer Engineering, National University of Singapore, advised by Prof. Vincent Y. F. Tan.
I obtained my Ph.D. (2024) in computer science from the National University of Singapore, advised by Prof. Xiaokui Xiao. Before that, I obtained my
master's degree in computer science at University of Science and Technology of China and my bachelor's degree in mathematics at
University of Science and Technology of China.

Contact

Email: tianyuan@nus.edu.sg

Recent Preprints

• Best Arm Identification with Minimal Regret
  Junwen Yang, Vincent Y. F. Tan, Tianyuan Jin.

• Multi-Armed Bandits with Abstention
  Junwen Yang, Tianyuan Jin, Vincent Y. F. Tan.

Selected Papers

* stands for the equal contribution.

• Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
  Tianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi
  Proceedings of the 38th Conference on Advances in Neural Information Processing Systems (NeurIPS 2024).

• Optimal Batched Best Arm Identification
  Tianyuan Jin, Yu Yang, Jing Tang, Xiaokui Xiao, Pan Xu
  Proceedings of the 38th Conference on Advances in Neural Information Processing Systems (NeurIPS 2024).

• Optimal Batched Linear Bandits
  Xuanfei Ren, Tianyuan Jin, Pan Xu
  Proceedings of the International Conference on Machine Learning (ICML 2024).

• Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs
  Tianyuan Jin, Hao-Lun Hsu, William Chang, Pan Xu
  Proceedings of Annual AAAI Conference on Artificial Intelligence (AAAI 2024). [Oral Presentation 2.3%]

• Thompson Sampling with Less Exploration is Fast and Optimal
  Tianyuan Jin, Xianglin Yang, Xiaokui Xiao, Pan Xu
  Proceedings of the International Conference on Machine Learning (ICML 2023).

• Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits
  Tianyuan Jin, Pan Xu, Xiaokui Xiao, Anima Anandkumar
  Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2022).

• Double Explore-then-Commit: Asymptotic Optimality and Beyond
  Tianyuan Jin, Pan Xu, Xiaokui Xiao, Quanquan Gu
  Proceedings of the Annual Conference on Learning Theory (COLT 2021). [arXiv]

• MOTS: Minimax Optimal Thompson Sampling
  Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao, Quanquan Gu
  Proceedings of the International Conference on Machine Learning (ICML 2021). [arXiv]

• Optimal Streaming Algorithms for Multi-Armed Bandits
  Tianyuan Jin, Keke Huang, Jing Tang, Xiaokui Xiao
  Proceedings of the International Conference on Machine Learning (ICML 2021).

• Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
  Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao, Quanquan Gu
  Proceedings of the International Conference on Machine Learning (ICML 2021).

• Unconstrained Submodular Maximization with Modular Costs: Tight Approximation and Application to Profit Maximization
  Tianyuan Jin, Yu Yang, Renchi Yang, Jieming Shi, Keke Huang, Xiaokui Xiao
  Proceedings of the VLDB Endowment (PVLDB 2021).
  This work has been presented at the ICML 2021 Subset Selection in Machine Learning: From Theory to Practice Workshop.

• Realtime Index-Free Single Source SimRank Processing on Web-Scale Graphs
  Jieming Shi*, Tianyuan Jin*, Renchi Yang, Xiaokui Xiao, Yin Yang
  Proceedings of the VLDB Endowment (PVLDB 2020)).

• Efficient Pure Exploration in Adaptive Round model
  Tianyuan Jin, Jieming Shi, Xiaokui Xiao, Enhong Chen
  Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2019).

Research Interests

• Online Learning and Bandits

• Submodularity

Award

• Google PhD Fellowship, 2021

• Research Achievement Award, School of Computing, National University of Singapore, 2021, 2023