| Oct 13, 2026 | 3 NeurIPS papers! Online RLHF with general preference model, fixed budget Monte Carlo tree search, and LLM fine tuning with GRPO with clipping replaced by signed logarithmic smoothing! |
| Oct 07, 2026 | We successfully co-organized the LeT workshop @ POSTECH! This workshop brought together learning theory researchers from across Korea for networking and discussion. |
| Sep 02, 2026 | The lab page has been renewed! |
| Jul 01, 2026 | Apr’26-Jul’26: 1 AISTATS, 1 ICLR, 2 ICML, 1 COLT, 1 TMLR |
| Jan 01, 2026 | Our lab has moved to POSTECH. It is one of the top research universities in South Korea! We are actively recruiting! |
| Jul 01, 2025 | 1 paper in ICML and 1 paper in COLT. |
| Jan 01, 2025 | 2 papers accepted to AISTATS! (i) Linear extension of the MED algorithm (or Maillard sampling) that is randomized, off-policy-friendly, and nearly optimal. (ii) Estimating the value of the maximum mean among K arms (rather than estimating who achieves it) that can surpass the performance of the oracle who knows the best arm and reports its sample mean! |
| Nov 01, 2024 | I gave a talk at UW-Madison SILO on ‘Confidence Sequences via Online Learning’ (video link). |
| Oct 01, 2024 | 2 papers accepted to NeurIPS: (i) led by Yao, bandit experiments with instrumental variables, so you can experiment when you can’t experiment! (ii) led by Junghyun, unified confidence sets for generalized linear models and finally removing the norm dependence in logistic bandits with novel regret analysis! |
| May 02, 2024 | 2 papers accepted to ICML: (i) adapting to the unknown noise level in linear bandits (ii) low-rank matrix recovery with better guarantees than the nuclear-norm regularization, how we can perform design of experiments for better subspace recovery, and how to solve low-rank bandits with them! |
| May 01, 2024 | 1 paper accepted to COLT on PAC-Bayes bounds with a different divergence that is better than KL! |
| Jan 01, 2024 | 1 paper accepted to AISTATS on converting a regret bound into a tight confidence set. Congrats Junghyun! |
| Dec 01, 2023 | 1 paper accepted to NeurIPS. Congrats Hao Qin! |
| Jul 01, 2023 | 1 paper accepted to COLT on a very tight PAC-Bayes bound! |
| Jul 01, 2023 | 1 paper accepted to ICML. Congrats to my student Yao and my collaborators Connor and Csaba! |
| Sep 01, 2022 | 2 papers accepted at NeurIPS. Congrats to my postdoc Kyoungseok Jang! |
| May 01, 2022 | I gave a talk at the RL theory virtual seminars on Maillard sampling. |
| Jan 01, 2022 | 1 paper accepted at AAAI, 3 papers accepted to AISTATS. |
| May 01, 2021 | 2 papers accepted at ICML. |
| May 01, 2021 | 1 paper accepted at ISIT. |
| Jul 01, 2020 | I gave a talk at the RL theory virtual seminars on structured bandits with the asymptotic optimality. |
| Jul 01, 2020 | Chicheng and I have a new work on structured bandits that is accepted to ICML’20 workshop on theoretical foundations of reinforcement learning! |
| Nov 01, 2019 | In Spring 2020, I will be teaching CSC 665 Online Learning and Multi-armed Bandits. |
| Oct 01, 2019 | Chicheng Zhang, Jason Pacheco, and I are organizing a machine learning reading group at UA. |
| Oct 01, 2019 | Our paper on kernel regression paper is accepted at NeurIPS’19. |
| Oct 01, 2019 | Our paper on parameter-free SGD with local differential privacy is accepted to PriML’19 (workshop at NeurIPS). |