The Equalized Odds (for short, EO) is one of the most popular measures of discrimination used in the supervised learning setting. It ascertains fairness through the balance of the misclassification rates (false positive and negative) across the protected groups -- e.g., in the context of law enforcement, an African-American defendant who would not commit a future crime will have an equal opportunity of being released, compared to a non-recidivating Caucasian defendant. Despite this noble goal, it has been acknowledged in the literature that statistical tests based on the EO are oblivious to the underlying causal mechanisms that generated the disparity in the first place (Hardt et al. 2016). This leads to a critical disconnect between statistical measures readable from the data and the meaning of discrimination in the legal system, where compelling evidence that the observed disparity is tied to a specific causal process deemed unfair by society is required to characterize discrimination. The goal of this paper is to develop a principled approach to connect the statistical disparities characterized by the EO and the underlying, elusive, and frequently unobserved, causal mechanisms that generated such inequality. We start by introducing a new family of counterfactual measures that allows one to explain the misclassification disparities in terms of the underlying mechanisms in an arbitrary, non-parametric structural causal model. This will, in turn, allow legal and data analysts to interpret currently deployed classifiers through causal lens, linking the statistical disparities found in the data to the corresponding causal processes. Leveraging the new family of counterfactual measures, we develop a learning procedure to construct a classifier that is statistically efficient, interpretable, and compatible with the basic human intuition of fairness. We demonstrate our results through experiments in both real (COMPAS) and synthetic datasets.

Obtaining human-interpretable explanations of large, general-purpose language models is an urgent goal for AI safety.

In many scientific applications, we observe a system in different conditions in which its components may change, rather than in isolation.

The PCMCI algorithm is proposed by Runge et al. [2019], aiming to detect time-lagged causal See Fig.1 for more detail. A simple proof is shown below through Markov assumption ( A2). 3 Figure 2: Partial causal graph for 3-variate time series Fig.2 shows a partial causal graph for a 3-variate time series with Semi-Stationary SCM. However, they may not share the same marginal distribution. Still in Fig.2, based on the definition of homogenous time partition, time partition subset Based on Eq.(12) and Eq.(17), we have: p(X Without loss of generality, we assume T is a multiple of δ all the time. A1-A7 and with an oracle (infinite sample size limit), we have that: null G = G (47) almost surely.

Discovering causal relations from observational time series without making the stationary assumption is a significant challenge.

Existing methods frequently assume causal sufficiency, disregarding the presence of unobserved confounding variables.

Despitethis noble goal, it has been acknowledged in the literature that statistical tests based ontheEOareoblivious totheunderlying causal mechanisms thatgenerated the disparity in the first place (Hardt et al. 2016).

However, it is known that even with infinite i.i.d.

Forexample, constraint-based methods exploit conditional independence relations between the variables in order to estimate the Markov equivalence classoftheunderlying causal graph [Spirtesetal.,2000;