Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

03/15/2020
by   Esther Rolf, et al.
0

While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts — online content recommendation and sustainable abalone fisheries — to underscore the applicability of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.

READ FULL TEXT

page 21

page 22

research
04/15/2022

Fairly Accurate: Learning Optimal Accuracy vs. Fairness Tradeoffs for Hate Speech Detection

Recent work has emphasized the importance of balancing competing objecti...
research
05/27/2019

Contest Architecture with Public Disclosures

I study optimal disclosure policies in sequential contests. A contest de...
research
05/27/2023

Optimization's Neglected Normative Commitments

Optimization is offered as an objective approach to resolving complex, r...
research
12/22/2022

Designing Equitable Transit Networks

Public transit is an essential infrastructure enabling access to employm...
research
05/01/2019

Fair Classification and Social Welfare

Now that machine learning algorithms lie at the center of many resource ...
research
10/19/2021

Learning Pareto-Efficient Decisions with Confidence

The paper considers the problem of multi-objective decision support when...

Please sign up or login with your details

Forgot password? Click here to reset