Counterfactual explanations and algorithmic recourses for machine learning: A review

S Verma, V Boonsanong, M Hoang, K Hines… - ACM Computing …, 2024 - dl.acm.org
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 …

An improved central limit theorem and fast convergence rates for entropic transportation costs

E del Barrio, AG Sanz, JM Loubes… - SIAM Journal on …, 2023 - SIAM
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 …

Weak limits of entropy regularized optimal transport; potentials, plans and divergences

A Gonzalez-Sanz, JM Loubes, J Niles-Weed - arxiv preprint arxiv …, 2022 - arxiv.org
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 …

Partial counterfactual identification of continuous outcomes with a curvature sensitivity model

V Melnychuk, D Frauen… - Advances in Neural …, 2023 - proceedings.neurips.cc
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 …

Central limit theorems for semi-discrete Wasserstein distances

E Del Barrio, A González Sanz, JM Loubes - Bernoulli, 2024 - projecteuclid.org
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 …

Weak limits for empirical entropic optimal transport: Beyond smooth costs

A González-Sanz, S Hundrieser - arxiv preprint arxiv:2305.09745, 2023 - arxiv.org
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 …

Counterfactual models for fair and adequate explanations

N Asher, L De Lara, S Paul, C Russell - Machine Learning and …, 2022 - mdpi.com
Recent efforts have uncovered various methods for providing explanations that can help
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

RA Berk, AK Kuchibhotla… - … Methods & Research, 2024 - journals.sagepub.com
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 …

A survey of identification and mitigation of machine learning algorithmic biases in image analysis

L Risser, A Picard, L Hervier, JM Loubes - arxiv preprint arxiv:2210.04491, 2022 - arxiv.org
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 …

Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models

M Il Idrissi, N Bousquet, F Gamboa… - Electronic Journal of …, 2024 - projecteuclid.org
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 …