Transport-based Counterfactual Models

反事实条件 反事实思维 计算机科学 因果模型 因果推理 数理经济学 计量经济学 推论 人工智能 经济 数学 心理学 统计 社会心理学
作者
Lucas de Lara,Alberto González-Sanz,Nicholas Asher,Laurent Risser,Jean–Michel Loubes
出处
期刊:Cornell University - arXiv 被引量:5
标识
DOI:10.48550/arxiv.2108.13025
摘要

Counterfactual frameworks have grown popular in machine learning for both explaining algorithmic decisions but also defining individual notions of fairness, more intuitive than typical group fairness conditions. However, state-of-the-art models to compute counterfactuals are either unrealistic or unfeasible. In particular, while Pearl's causal inference provides appealing rules to calculate counterfactuals, it relies on a model that is unknown and hard to discover in practice. We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model. We define transport-based counterfactual models as collections of joint probability distributions between observable distributions, and show their connection to causal counterfactuals. More specifically, we argue that optimal-transport theory defines relevant transport-based counterfactual models, as they are numerically feasible, statistically-faithful, and can coincide under some assumptions with causal counterfactual models. Finally, these models make counterfactual approaches to fairness feasible, and we illustrate their practicality and efficiency on fair learning. With this paper, we aim at laying out the theoretical foundations for a new, implementable approach to counterfactual thinking.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
mimilv发布了新的文献求助10
刚刚
刚刚
1秒前
1秒前
chris发布了新的文献求助10
2秒前
爆米花应助r8211采纳,获得10
2秒前
2秒前
3秒前
3秒前
4秒前
4秒前
4秒前
QiranSheng完成签到,获得积分10
4秒前
星落枝头发布了新的文献求助10
4秒前
Akim应助科研小白采纳,获得10
5秒前
66完成签到,获得积分20
5秒前
5秒前
美丽无血发布了新的文献求助10
6秒前
寒冷的匪完成签到,获得积分10
7秒前
科研通AI5应助Moran采纳,获得10
7秒前
科研通AI5应助xiaoruirx采纳,获得30
7秒前
7秒前
沫荔发布了新的文献求助10
7秒前
Henry发布了新的文献求助10
8秒前
8秒前
科目三应助DreamerKing采纳,获得10
8秒前
大个应助无尘泪采纳,获得10
9秒前
66发布了新的文献求助30
9秒前
汉堡包应助百灵鸟采纳,获得10
9秒前
杨震发布了新的文献求助10
10秒前
清爽伯云发布了新的文献求助10
11秒前
万能图书馆应助粗犷的磬采纳,获得10
11秒前
阿秋发布了新的文献求助30
12秒前
小猫咪发布了新的文献求助10
12秒前
玉玉完成签到,获得积分10
12秒前
SciGPT应助cch采纳,获得10
12秒前
英俊的铭应助土拨鼠采纳,获得10
12秒前
领导范儿应助chris采纳,获得10
13秒前
13秒前
13秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Technologies supporting mass customization of apparel: A pilot project 450
China—Art—Modernity: A Critical Introduction to Chinese Visual Expression from the Beginning of the Twentieth Century to the Present Day 430
Tip60 complex regulates eggshell formation and oviposition in the white-backed planthopper, providing effective targets for pest control 400
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
China Gadabouts: New Frontiers of Humanitarian Nursing, 1941–51 400
The Healthy Socialist Life in Maoist China, 1949–1980 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3790524
求助须知:如何正确求助?哪些是违规求助? 3335294
关于积分的说明 10274188
捐赠科研通 3051766
什么是DOI,文献DOI怎么找? 1674822
邀请新用户注册赠送积分活动 802870
科研通“疑难数据库(出版商)”最低求助积分说明 760956