Causal Covariate Shift Correction using Fisher information penalty

We also present the baselines, datasets details, C 3 batchwise performance λ selection details, and experimental setup. A.1 R EPRESENTING THE CURRENT DERIVATIVE WITH THE F ISHER INFORMATION MATRIX Let us consider having a model with parameter θ and a likelihood function p (X | θ), where X is observed data. The estimate of true parameter θ can be found by using estimator ˆ θ . The Fisher information I (θ) can be defined as the expected value of the negative hessian of the log-likelihood function. I (θ) = E null 2 log p (X | θ) θ θ T null (4) The Cram er-Rao Lower Bound (CRLB) states that for any unbiased estimator ˆ θ, the variance-covariance matrix V ( ˆ θ) satisfies the inequality property: V ( ˆ θ) I 1 (θ) (5) The symbol represents the following matrix inequality V ( ˆ θ) I 1 (θ) positive and semi-definite.