On the Adversarial Robustness of Causal Algorithmic Recourse

12/21/2021
by   Ricardo Dominguez-Olmedo, et al.
4

Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable outcomes made by automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods offering minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse in the linear and in the differentiable case. To ensure that recourse is robust, individuals are asked to make more effort than they would have otherwise had to. In order to shift part of the burden of robustness from the decision-subject to the decision-maker, we propose a model regularizer that encourages the additional cost of seeking robust recourse to be low. We show that classifiers trained with our proposed model regularizer, which penalizes relying on unactionable features for prediction, offer potentially less effortful recourse.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2023

Robustness Implies Fairness in Casual Algorithmic Recourse

Algorithmic recourse aims to disclose the inner workings of the black-bo...
research
02/08/2021

Designing for Contestation: Insights from Administrative Law

A paper presented at the Workshop on Contestability in Algorithmic Syste...
research
09/13/2023

Setting the Right Expectations: Algorithmic Recourse Over Time

Algorithmic systems are often called upon to assist in high-stakes decis...
research
12/04/2020

Experimental Evaluation of Algorithm-Assisted Human Decision-Making: Application to Pretrial Public Safety Assessment

Despite an increasing reliance on fully-automated algorithmic decision m...
research
07/13/2018

How Do Classifiers Induce Agents To Invest Effort Strategically?

Machine learning is often used to produce decision-making rules that cla...
research
05/19/2021

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

Robustness of decision rules to shifts in the data-generating process is...
research
09/28/2022

B2B Advertising: Joint Dynamic Scoring of Account and Users

When a business sells to another business (B2B), the buying business is ...

Please sign up or login with your details

Forgot password? Click here to reset