SyncAI.news, a Varaisys broadcasting
Sharp Characterization of Bias in Post-Bandit Inference
LW

Lisu Wang, Yilun Chen, Jiaqi Lu

· 1 min read

ResearcharXiv cs.LG

Sharp Characterization of Bias in Post-Bandit Inference

arXiv:2608.01069v2 Announce Type: replace Abstract: 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 and its generalizations, and derive sharp leading-order expressions for the sample-mean bias and expected $Z$-statistic, in bandit experiments of fixed horizon $T$. Our characterization reveals the algorithmic origin of bias through a key index-function-dependent quantity, which we term effective exploration rate. For example, under UCB1, the effective exploration rate is of order $\sqrt{\log T}$, and the standardized bias of any arm (that is not uniquely optimal) decays at the extremely slow rate $1/\sqrt{\log T}$. We also show how the choice of the index function affects both regret and bias, which reveals a regret-bias trade-off: more exploratory algorithm reduces bias but increases regret. We further show how bias most severely distorts confidence intervals and hypothesis tests when the tested arm is one of the tied-optimal arms. Our sharp characterization for bias uses a novel empirical fluid approximation of the algorithm's sampling dynamics, which may be of independent interest.

Original source

This story was published by arXiv cs.LG and written by Lisu Wang, Yilun Chen, Jiaqi Lu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News