PaperScope
LIVE · 2026-09-29 05:40 UTC

FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions

Haijie Xu, Chen Zhang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.32165 v1
Category
Submitted
2026-09-26

Abstract

We study fully online fixed-confidence causal discovery without any historical observational data. Starting from zero samples, the learner sequentially selects interventions to recover both the causal DAG and its edge weights under a linear-Gaussian structural equation model. We establish an instance-dependent lower bound for any $(ε,δ)$-correct algorithm and propose \textsc{FOCUS}, which adaptively allocates interventions through an online max--min game. A key contribution is a computable concentration inequality for the accumulated KL divergence involving causal parameters shared across interventions. We prove that \textsc{FOCUS} is $(ε,δ)$-correct and that its expected stopping time matches the lower bound in its $Θ(\log(1/δ))$ dependence up to an instance-dependent constant. Experiments demonstrate improved structure and edge-weight recovery and confirm the predicted stopping-time trend. Our codes are available on https://anonymous.4open.science/r/FOCUS_code-76E5

arXiv abs page · PDF · same-day batch