Counterfactual explanations and algorithmic recourses for machine learning: A review
Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …
difficult or impossible to understand by human stakeholders. Explaining, in a human …
An improved central limit theorem and fast convergence rates for entropic transportation costs
We prove a central limit theorem for the entropic transportation cost between subgaussian
probability measures, centered at the population cost. This is the first result which allows for …
probability measures, centered at the population cost. This is the first result which allows for …
Weak limits of entropy regularized optimal transport; potentials, plans and divergences
This work deals with the asymptotic distribution of both potentials and couplings of entropic
regularized optimal transport for compactly supported probabilities in $\R^ d $. We first …
regularized optimal transport for compactly supported probabilities in $\R^ d $. We first …
Partial counterfactual identification of continuous outcomes with a curvature sensitivity model
Counterfactual inference aims to answer retrospective" what if" questions and thus belongs
to the most fine-grained type of inference in Pearl's causality ladder. Existing methods for …
to the most fine-grained type of inference in Pearl's causality ladder. Existing methods for …
Central limit theorems for semi-discrete Wasserstein distances
The supplementary material contains simulations of the sharpness of the upper bound given
in Theorem 3.2. It also includes simulations of the asymptotic results of Theorems 2.4 and …
in Theorem 3.2. It also includes simulations of the asymptotic results of Theorems 2.4 and …
Weak limits for empirical entropic optimal transport: Beyond smooth costs
We establish weak limits for the empirical entropy regularized optimal transport cost, the
expectation of the empirical plan and the conditional expectation. Our results require only …
expectation of the empirical plan and the conditional expectation. Our results require only …
Counterfactual models for fair and adequate explanations
Recent efforts have uncovered various methods for providing explanations that can help
interpret the behavior of machine learning programs. Exact explanations with a rigorous …
interpret the behavior of machine learning programs. Exact explanations with a rigorous …
Improving fairness in criminal justice algorithmic risk assessments using optimal transport and conformal prediction sets
In the United States and elsewhere, risk assessment algorithms are being used to help
inform criminal justice decision-makers. A common intent is to forecast an offender's “future …
inform criminal justice decision-makers. A common intent is to forecast an offender's “future …
A survey of identification and mitigation of machine learning algorithmic biases in image analysis
The problem of algorithmic bias in machine learning has gained a lot of attention in recent
years due to its concrete and potentially hazardous implications in society. In much the same …
years due to its concrete and potentially hazardous implications in society. In much the same …
Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models
Robustness studies of black-box models is recognized as a necessary task for numerical
models based on structural equations and predictive models learned from data. These …
models based on structural equations and predictive models learned from data. These …