Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning

稳健优化 计算机科学 数学优化 人工智能 数学
作者
Daniel Kühn,Peyman Mohajerin Esfahani,Viet Anh Nguyen,Soroosh Shafieezadeh-Abadeh
标识
DOI:10.1287/educ.2019.0198
摘要

Many decision problems in science, engineering and economics are affected by uncertain parameters whose distribution is only indirectly observable through samples. The goal of data-driven decision-making is to learn a decision from finitely many training samples that will perform well on unseen test samples. This learning task is difficult even if all training and test samples are drawn from the same distribution---especially if the dimension of the uncertainty is large relative to the training sample size. Wasserstein distributionally robust optimization seeks data-driven decisions that perform well under the most adverse distribution within a certain Wasserstein distance from a nominal distribution constructed from the training samples. In this tutorial we will argue that this approach has many conceptual and computational benefits. Most prominently, the optimal decisions can often be computed by solving tractable convex optimization problems, and they enjoy rigorous out-of-sample and asymptotic consistency guarantees. We will also show that Wasserstein distributionally robust optimization has interesting ramifications for statistical learning and motivates new approaches for fundamental learning tasks such as classification, regression, maximum likelihood estimation or minimum mean square error estimation, among others.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
小袁发布了新的文献求助10
1秒前
胖豆儿完成签到 ,获得积分10
1秒前
吴昊东发布了新的文献求助10
1秒前
2秒前
seal发布了新的文献求助10
3秒前
张张张发布了新的文献求助10
4秒前
yang完成签到,获得积分10
4秒前
一手灵魂完成签到,获得积分10
7秒前
花花草草发布了新的文献求助10
7秒前
云隐完成签到,获得积分10
7秒前
Ayu完成签到,获得积分10
10秒前
灵溪完成签到 ,获得积分10
11秒前
12秒前
小马甲应助xiaozheng采纳,获得10
13秒前
xu完成签到 ,获得积分10
15秒前
负责的寻云完成签到,获得积分20
15秒前
可爱的函函应助无解采纳,获得10
15秒前
汉堡包应助yoyo122采纳,获得10
15秒前
研友_nVqwxL发布了新的文献求助10
15秒前
乐乐应助seal采纳,获得10
16秒前
JamesPei应助科研通管家采纳,获得10
17秒前
852应助科研通管家采纳,获得10
17秒前
搜集达人应助科研通管家采纳,获得10
17秒前
天天快乐应助科研通管家采纳,获得10
17秒前
劲秉应助科研通管家采纳,获得10
17秒前
17秒前
17秒前
17秒前
26完成签到 ,获得积分10
18秒前
Orange应助枯夏采纳,获得10
19秒前
wss533完成签到,获得积分10
24秒前
25秒前
思源应助xu采纳,获得10
25秒前
27秒前
清脆如娆完成签到 ,获得积分10
30秒前
30秒前
32秒前
NexusExplorer应助不会取名字采纳,获得10
33秒前
鹏826发布了新的文献求助10
33秒前
CodeCraft应助wanci采纳,获得10
33秒前
高分求助中
Licensing Deals in Pharmaceuticals 2019-2024 3000
Effect of reactor temperature on FCC yield 2000
Very-high-order BVD Schemes Using β-variable THINC Method 1020
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Mission to Mao: Us Intelligence and the Chinese Communists in World War II 600
The Conscience of the Party: Hu Yaobang, China’s Communist Reformer 600
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3299813
求助须知:如何正确求助?哪些是违规求助? 2934662
关于积分的说明 8470165
捐赠科研通 2608229
什么是DOI,文献DOI怎么找? 1424075
科研通“疑难数据库(出版商)”最低求助积分说明 661827
邀请新用户注册赠送积分活动 645574