AI.info

Min-hwan Oh

Explore Min-hwan Oh on AI.info.

• Generalized Linear Bandits with Memory
• Convergence of Muon with Newton-Schulz
• Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
• ADAM Optimization with Adaptive Batch Selection
• Thompson Sampling for Multi-Objective Linear Contextual Bandit
• Infrequent Exploration in Linear Bandits
• Oracle-Efficient Combinatorial Semi-Bandits
• Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
• Exploration via Feature Perturbation in Contextual Bandits
• Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality