5 papers
Characterizing Bias in Post-Bandit Inference under Index Algorithms
Lisu Wang, Yilun Chen, Jiaqi Lu
Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 an…
Bandit Allocational Instability
Yilun Chen, Jiaqi Lu
When multi-armed bandit (MAB) algorithms allocate pulls among competing arms, the resulting allocation can exhibit huge variation. This is particularly harmful in modern applicatio…
Online Stochastic Packing with General Correlations
Sabri Cetin, Yilun Chen, David A. Goldberg
There has been a growing interest in studying online stochastic packing under more general correlation structures, motivated by the complex data sets and models driving modern appl…
A characterization of sample adaptivity in UCB data
Yilun Chen, Jiaqi Lu
We characterize a joint CLT of the number of pulls and the sample mean reward of the arms in a stochastic two-armed bandit environment under UCB algorithms. Several implications of…
Beyond Non-Degeneracy: Revisiting Certainty Equivalent Heuristic for Online Linear Programming
Yilun Chen, Wenjia Wang
The Certainty Equivalent heuristic (CE) is a widely-used algorithm for various dynamic resource allocation problems in OR and OM. Despite its popularity, existing theoretical guara…