274 citations · 408 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Sharp Characterization of Bias in Post-Bandit Inference
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…
cs.LG2026
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…