paper-with-me

Papers

Counterfactual Explanations for Linear Optimization

2024-05-24 · Jannis Kurtz, Ş. İlker Birbil, Dick den Hertog

The concept of counterfactual explanations (CE) has emerged as one of the important concepts to understand the inner workings of complex AI systems. In this paper, we translate the idea of CEs to linear optimization and propose, motivate, and analyze three different types of CEs: strong, weak, and relative. While deriving strong and weak CEs appears to be computationally intractable, we show that calculating relative CEs can be done efficiently. By detecting and exploiting the hidden convex structure of the optimization problem that arises in the latter case, we show that obtaining relative CEs can be done in the same magnitude of time as solving the original linear optimization problem. This is confirmed by an extensive numerical experiment study on the NETLIB library.

📄 PDF Abstract BibTeX arXiv:2405.15431

Code (1)

JannisKu/CE4LOPT 공식 구현

Tasks

counterfactual

Similar Papers 제목 키워드 기반

Optimal Transport Group Counterfactual Explanations

2026-01-28 · Enrique Valero-Leal, Bernd Bischl, Pedro Larrañaga, Concha Bielza 외 arxiv

Group counterfactual explanations find a set of counterfactual instances to explain a group of input instances contrastively. However, existing methods either (i) optimize counterfactuals only for a fixed group and do no…

CF-OPT: Counterfactual Explanations for Structured Prediction

2024-05-28 · Germain Vivier-Ardisson, Alexandre Forel, Axel Parmentier, Thibaut Vidal

Optimization layers in deep neural networks have enjoyed a growing popularity in structured learning, improving the state of the art on a variety of applications. Yet, these pipelines lack interpretability since they are…

counterfactualPredictionStructured Prediction

Counterfactual Explanations for Support Vector Machine Models

2022-12-14 · Sebastian Salazar, Samuel Denton, Ansaf Salleb-Aouissi

We tackle the problem of computing counterfactual explanations -- minimal changes to the features that flip an undesirable model prediction. We propose a solution to this question for linear Support Vector Machine (SVMs)…

counterfactualvalid

Convex optimization for actionable \& plausible counterfactual explanations

2021-05-17 · André Artelt, Barbara Hammer

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and …

counterfactualDecision Making

Counterfactual Explanations Using Optimization With Constraint Learning

2022-09-22 · Donato Maragno, Tabea E. Röber, Ilker Birbil

To increase the adoption of counterfactual explanations in practice, several criteria that these should adhere to have been put forward in the literature. We propose counterfactual explanations using optimization with co…

counterfactualDiversity