On the Adversarial Robustness of Causal Algorithmic Recourse
- URL: http://arxiv.org/abs/2112.11313v1
- Date: Tue, 21 Dec 2021 16:00:54 GMT
- Title: On the Adversarial Robustness of Causal Algorithmic Recourse
- Authors: Ricardo Dominguez-Olmedo, Amir-Hossein Karimi, Bernhard Sch\"olkopf
- Abstract summary: Recourse recommendations should ideally be robust to reasonably small uncertainty.
We show that recourse methods offering minimally costly recourse fail to be robust.
We propose a model regularizer that encourages the additional cost of seeking robust recourse to be low.
- Score: 2.1132376804211543
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations [80.86128012438834]
We show for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete.
We propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees.
arXiv Detail & Related papers (2024-07-10T09:13:11Z) - Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation [18.423687983628145]
Algorithmic recourse recommends a cost-efficient action to a subject to reverse an unfavorable machine learning classification decision.
This paper proposes a two-step approach integrating preference learning into the recourse generation problem.
arXiv Detail & Related papers (2024-02-23T03:27:17Z) - Robustness Implies Fairness in Casual Algorithmic Recourse [13.86376549140248]
Algorithmic recourse aims to disclose the inner workings of the black-box decision process in situations where decisions have significant consequences.
To ensure an effective remedy, suggested interventions must not only be low-cost but also robust and fair.
This study explores the concept of individual fairness and adversarial robustness in causal algorithmic recourse.
arXiv Detail & Related papers (2023-02-07T13:40:56Z) - Incentive-Aware Recommender Systems in Two-Sided Markets [49.692453629365204]
We propose a novel recommender system that aligns with agents' incentives while achieving myopically optimal performance.
Our framework models this incentive-aware system as a multi-agent bandit problem in two-sided markets.
Both algorithms satisfy an ex-post fairness criterion, which protects agents from over-exploitation.
arXiv Detail & Related papers (2022-11-23T22:20:12Z) - Algorithmic Assistance with Recommendation-Dependent Preferences [2.864550757598007]
We consider the effect and design of algorithmic recommendations when they affect choices.
We show that recommendation-dependent preferences create inefficiencies where the decision-maker is overly responsive to the recommendation.
arXiv Detail & Related papers (2022-08-16T09:24:47Z) - Probabilistically Robust Recourse: Navigating the Trade-offs between
Costs and Robustness in Algorithmic Recourse [34.39887495671287]
We propose an objective function which simultaneously minimizes the gap between the achieved (resulting) and desired recourse invalidation rates.
We develop novel theoretical results to characterize the recourse invalidation rates corresponding to any given instance.
Experimental evaluation with multiple real world datasets demonstrates the efficacy of the proposed framework.
arXiv Detail & Related papers (2022-03-13T21:39:24Z) - Bayesian Persuasion for Algorithmic Recourse [28.586165301962485]
In some situations, the underlying predictive model is deliberately kept secret to avoid gaming.
This opacity forces the decision subjects to rely on incomplete information when making strategic feature modifications.
We capture such settings as a game of Bayesian persuasion, in which the decision-maker sends a signal, e.g., an action recommendation, to a decision subject to incentivize them to take desirable actions.
arXiv Detail & Related papers (2021-12-12T17:18:54Z) - Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk.
Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
arXiv Detail & Related papers (2021-06-11T16:49:15Z) - Outcome-Driven Reinforcement Learning via Variational Inference [95.82770132618862]
We discuss a new perspective on reinforcement learning, recasting it as the problem of inferring actions that achieve desired outcomes, rather than a problem of maximizing rewards.
To solve the resulting outcome-directed inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function.
We empirically demonstrate that this method eliminates the need to design reward functions and leads to effective goal-directed behaviors.
arXiv Detail & Related papers (2021-04-20T18:16:21Z) - Confidence-Budget Matching for Sequential Budgeted Learning [69.77435313099366]
We formalize decision-making problems with querying budget.
We consider multi-armed bandits, linear bandits, and reinforcement learning problems.
We show that CBM based algorithms perform well in the presence of adversity.
arXiv Detail & Related papers (2021-02-05T19:56:31Z) - Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
empowerment principle enables unsupervised stabilization of dynamical systems at upright positions.
We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel.
We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
arXiv Detail & Related papers (2020-07-14T21:10:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.