Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Learning-Augmented Robust Algorithmic Recourse
02 Oct 2024
Abstract
The widespread use of machine learning models in high-stakes domains can have
a major negative impact, especially on individuals who receive undesirable
outcomes. Algorithmic recourse provides such individuals with suggestions of
minimum-cost improvements they can make to achieve a desirable outcome in the
future. However, machine learning models often get updated over time and this
can cause a recourse to become invalid (i.e., not lead to the desirable
outcome). The robust recourse literature aims to choose recourses that are less
sensitive, even against adversarial model changes, but this comes at a higher
cost. To overcome this obstacle, we initiate the study of algorithmic recourse
through the learning-augmented framework and evaluate the extent to which a
designer equipped with a prediction regarding future model changes can reduce
the cost of recourse when the prediction is accurate (consistency) while also
limiting the cost even when the prediction is inaccurate (robustness). We
propose a novel algorithm for this problem, study the robustness-consistency
trade-off, and analyze how prediction accuracy affects performance.
Metrics
14 Record Views
Details
- Title
- Learning-Augmented Robust Algorithmic Recourse
- Creators
- Kshitij KayasthaVasilis GkatzelisShahin Jabbari
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science
- Other Identifier
- 991021906082004721