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
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
左安完成签到,获得积分10
刚刚
1秒前
知性的囧完成签到,获得积分10
1秒前
1秒前
abc123发布了新的文献求助10
1秒前
讨厌所有人完成签到,获得积分10
1秒前
2秒前
psj完成签到,获得积分10
2秒前
852应助枫溪采纳,获得10
2秒前
3秒前
4秒前
shadow完成签到 ,获得积分10
6秒前
万能图书馆应助小刺猬采纳,获得30
6秒前
滴答发布了新的文献求助30
6秒前
6秒前
6秒前
沅期发布了新的文献求助10
7秒前
7秒前
量子星尘发布了新的文献求助10
8秒前
俭朴奇异果完成签到,获得积分10
9秒前
橙鹿鹿的猫完成签到,获得积分10
9秒前
9秒前
边港洋发布了新的文献求助10
11秒前
11秒前
12秒前
量子星尘发布了新的文献求助10
12秒前
13秒前
14秒前
笨男孩发布了新的文献求助10
14秒前
15秒前
15秒前
wanghao发布了新的文献求助10
15秒前
陈湫完成签到,获得积分10
16秒前
田様应助等待的寒松采纳,获得10
16秒前
害怕的白竹完成签到,获得积分10
17秒前
随心完成签到,获得积分10
17秒前
怕孤单的嚣完成签到,获得积分20
17秒前
lcxw1224完成签到,获得积分10
17秒前
18秒前
长常九久发布了新的文献求助10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Clinical Microbiology Procedures Handbook, Multi-Volume, 5th Edition 2000
The Cambridge History of China: Volume 4, Sui and T'ang China, 589–906 AD, Part Two 1000
The Composition and Relative Chronology of Dynasties 16 and 17 in Egypt 1000
Russian Foreign Policy: Change and Continuity 800
Real World Research, 5th Edition 800
Qualitative Data Analysis with NVivo By Jenine Beekhuyzen, Pat Bazeley · 2024 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 计算机科学 有机化学 物理 生物化学 纳米技术 复合材料 内科学 化学工程 人工智能 催化作用 遗传学 数学 基因 量子力学 物理化学
热门帖子
关注 科研通微信公众号,转发送积分 5718021
求助须知:如何正确求助?哪些是违规求助? 5250051
关于积分的说明 15284272
捐赠科研通 4868198
什么是DOI,文献DOI怎么找? 2614063
邀请新用户注册赠送积分活动 1563973
关于科研通互助平台的介绍 1521425