Such assumptions allow for identification of causal target parameters. For instance, one may be interested in the average variance-weighted treatment effects (Robins et al., 2008; Li et al., 2011),

Missing values in real-world data pose a significant and unique challenge to algorithmic fairness.

However, evaluating whether or not these approximations can be trusted remains a challenge. Most approaches evaluate the posterior estimator only in expectation over the observation space.

MI can lead to the disclosure of highly sensitive information about the individual, e.g. that