|国家预印本平台
首页|Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality

Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality

Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality

来源:Arxiv_logoArxiv
英文摘要

The article explores the emerging domain of incentive-aware machine learning (ML), which focuses on algorithmic decision-making in contexts where individuals can strategically modify their inputs to influence outcomes. It categorizes the research into three perspectives: robustness, aiming to design models resilient to "gaming"; fairness, analyzing the societal impacts of such systems; and improvement/causality, recognizing situations where strategic actions lead to genuine personal or societal improvement. The paper introduces a unified framework encapsulating models for these perspectives, including offline, online, and causal settings, and highlights key challenges such as differentiating between gaming and improvement and addressing heterogeneity among agents. By synthesizing findings from diverse works, we outline theoretical advancements and practical solutions for robust, fair, and causally-informed incentive-aware ML systems.

Chara Podimata

计算技术、计算机技术

Chara Podimata.Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality[EB/OL].(2025-05-08)[2025-06-27].https://arxiv.org/abs/2505.05211.点此复制

评论