| 2026 | COLT | Avoiding exp(k | Tianyuan Jin, Heyang Zhao, Vincent Y. F. Tan, Quanquan Gu |
| 2025 | ICLR | Breaking the log(1/Δ2) Barrier: Better Batched Best Arm Identification with Adaptive Grids. | Tianyuan Jin, Qin Zhang, Dongruo Zhou |
| 2024 | AAAI | Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs. | Tianyuan Jin, Hao-Lun Hsu, William Chang, Pan Xu |
| 2024 | ICML | Optimal Batched Linear Bandits. | Xuanfei Ren, Tianyuan Jin, Pan Xu |
| 2023 | ICML | Thompson Sampling with Less Exploration is Fast and Optimal. | Tianyuan Jin, Xianglin Yang, Xiaokui Xiao, Pan Xu |
| 2021 | COLT | Double Explore-then-Commit: Asymptotic Optimality and Beyond. | Tianyuan Jin, Pan Xu, Xiaokui Xiao, Quanquan Gu |
| 2021 | ICML | MOTS: Minimax Optimal Thompson Sampling. | Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao, Quanquan Gu |
| 2021 | ICML | Optimal Streaming Algorithms for Multi-Armed Bandits. | Tianyuan Jin, Keke Huang, Jing Tang, Xiaokui Xiao |
| 2021 | ICML | Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits. | Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao, Quanquan Gu |
| 2019 | CIKM | Tracking Top-k Influential Users with Relative Errors. | Yu Yang, Zhefeng Wang, Tianyuan Jin, Jian Pei, Enhong Chen |
| 2018 | SDM | Maximizing the Effect of Information Adoption: A General Framework. | Tianyuan Jin, Tong Xu, Hui Zhong, Enhong Chen, Zhefeng Wang, Qi Liu |