In the causal bandit setup, we propose a two-stage approach.

Before deploying any newly developed policy, it is important to assess its impact. In many high-stakes domains, it is risky or unethical to implement such policies directly for online evaluation.

Neural Information Processing Systems http://nips.cc/

Thistask is challenging because the causal graph is unknown and even there may exist latent confounders.

Thistask is challenging because the causal graph is unknown and even there may exist latent confounders.

Evaluating novel contextual bandit policies using logged data is crucial in applications where exploration is costly, such as medicine. But it usually relies on the assumption of no unobserved confounders, which is bound to fail in practice. We study the question of policy evaluation when we instead have proxies for the latent confounders and develop an importance weighting method that avoids fitting a latent outcome regression model. Surprisingly, we show that there exist no single set of weights that give unbiased evaluation regardless of outcome model, unlike the case with no unobserved confounders where density ratios are sufficient. Instead, we propose an adversarial objective and weights that minimize it, ensuring sufficient balance in the latent confounders regardless of outcome model. We develop theory characterizing the consistency of our method and tractable algorithms for it. Empirical results validate the power of our method when confounders are latent.

We present a new method for linear and nonlinear, lagged and contemporaneous constraint-based causal discovery from observational time series in the presence of latent confounders. We show that existing causal discovery methods such as FCI and variants suffer from low recall in the autocorrelated time series case and identify low effect size of conditional independence tests as the main reason. Information-theoretical arguments show that effect size can often be increased if causal parents are included in the conditioning sets. To identify parents early on, we suggest an iterative procedure that utilizes novel orientation rules to determine ancestral relationships already during the edge removal phase. We prove that the method is order-independent, and sound and complete in the oracle case. Extensive simulation studies for different numbers of variables, time lags, sample sizes, and further cases demonstrate that our method indeed achieves much higher recall than existing methods for the case of autocorrelated continuous variables while keeping false positives at the desired level. This performance gain grows with stronger autocorrelation.