paper-with-me

홈 › Papers

Using Property Elicitation to Understand the Impacts of Fairness Regularizers

2023-09-20 · Jessie Finocchiaro

Predictive algorithms are often trained by optimizing some loss function, to which regularization functions are added to impose a penalty for violating constraints. As expected, the addition of such regularization functions can change the minimizer of the objective. It is not well-understood which regularizers change the minimizer of the loss, and, when the minimizer does change, how it changes. We use property elicitation to take first steps towards understanding the joint relationship between the loss and regularization functions and the optimal decision for a given problem instance. In particular, we give a necessary and sufficient condition on loss and regularizer pairs for when a property changes with the addition of the regularizer, and examine some regularizers satisfying this condition standard in the fair machine learning literature. We empirically demonstrate how algorithmic decision-making changes as a function of both data distribution changes and hardness of the constraints.

📄 PDF Abstract BibTeX arXiv:2309.11343

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingFairness

Similar Papers 제목 키워드 기반

Fair Performance Metric Elicitation

2020-06-23 · NeurIPS 2020 12 · Gaurush Hiranandani, Harikrishna Narasimhan, Oluwasanmi Koyejo

What is a fair performance metric? We consider the choice of fairness metrics through the lens of metric elicitation -- a principled framework for selecting performance metrics that best reflect implicit preferences. The…

Fairness

Post-processing of Differentially Private Data: A Fairness Perspective

2022-01-24 · Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck

Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees. Post-process…

Fairness

A Convex Framework for Fair Regression

2017-06-07 · Richard Berk, Hoda Heidari, Shahin Jabbari, Matthew Joseph 외

We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fa…

Fairnessregression

Quadratic Metric Elicitation for Fairness and Beyond

2020-11-03 · Gaurush Hiranandani, Jatin Mathur, Harikrishna Narasimhan, Oluwasanmi Koyejo

Metric elicitation is a recent framework for eliciting classification performance metrics that best reflect implicit user preferences based on the task and context. However, available elicitation strategies have been lim…

Fairness

Property Elicitation on Imprecise Probabilities

2025-07-08 · James Bailie, Rabanus Derr arxiv

Property elicitation studies which attributes of a probability distribution can be determined by minimizing a risk. We investigate a generalization of property elicitation to imprecise probabilities (IP). This investigat…