2 papers
cs.LG2026
MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits
Xin Li, Zixin Zhong
We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic lin…
math.OC2026
How much Data do We Need? Sequential Data Collection for Stochastic Programming
Xin Li, Juergen Branke, Xuan Vinh Doan
Data-driven optimization often requires collecting data to estimate uncertain model parameters before solving the underlying decision problem. In practice, however, data acquisitio…