Publications

Taehyun Hwang, Min-hwan Oh (2026). Linear Ensemble Sampling with Smaller Ensembles. NeurIPS 2026.

Taehyun Hwang, Hyunjun Choi, Heesang Ann, Min-hwan Oh (2026). Block Optimism for Nonstationary Bandits with Latent Linear Dynamics. NeurIPS 2026.

Hyunjun Choi, Taehyun Hwang, Min-hwan Oh (2026). Topic-Aware Contextual Cascading Bandits. NeurIPS 2026.

Heesang Ann, Hyunjun Choi, Taehyun Hwang, Younghoon Shin, Haeju Cheong, Min-hwan Oh (2026). Generalized Linear Bandits with Memory. ICML 2026.

Heesang Ann, Taehyun Hwang, Min-hwan Oh (2026). Diversified Multinomial Logit Contextual Bandits. ICLR 2026.

Taehyun Hwang, Dahngoon Kim, Min-hwan Oh (2025). Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities. NeurIPS 2025.

Harin Lee, Taehyun Hwang, Min-hwan Oh (2025). Lasso Bandit with Compatibility Condition on Optimal Arm. ICLR 2025.

Wooseong Cho, Taehyun Hwang, Joongkyu Lee, Min-hwan Oh (2024). Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation. NeurIPS 2024.

Taehyun Hwang, Kyuwook Chai, Min-hwan Oh (2023). Combinatorial Neural Bandits. ICML 2023.

Taehyun Hwang, Min-hwan Oh (2022). Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation. AAAI 2023 [Oral presentation].