RSOME in Python: An Open-Source Package for Robust Stochastic Optimization Made Easy

Zhi Chen; Peng Xiong

doi:10.1287/ijoc.2023.1291

RSOME in Python: An Open-Source Package for Robust Stochastic Optimization Made Easy

Zhi Chen, Peng Xiong^*

^*Corresponding author for this work

College of Business

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

15 Citations (Scopus)

Abstract

We introduce a Python package called RSOME for modeling a wide spectrum of robust and distributionally robust optimization problems. RSOME serves as an open-source framework for modeling various optimization problems subject to distributional ambiguity in a highly readable and mathematically intuitive manner. It is versatile and fits well in the open-source software community in the sense that (i) it is consistent with NumPy arrays in indexing and slicing and; (ii) together with the rich Python libraries for machine learning, data analysis, and visualization, it is easy to implement data-driven models; and (iii) it pro-vides convenient interfaces for users to switch and tune parameters among different solvers.

© 2023 INFORMS

Original language	English
Pages (from-to)	717-724
Journal	INFORMS Journal on Computing
Volume	35
Issue number	4
Online published	30 Mar 2023
DOIs	https://doi.org/10.1287/ijoc.2023.1291
Publication status	Published - Jul 2023

Research Keywords

(distributionally) robust optimization
algebraic modeling package
adaptive decision making
data-driven analytics

Access Output

10.1287/ijoc.2023.1291

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{e9329900271740648072404f3d63a484,

title = "RSOME in Python: An Open-Source Package for Robust Stochastic Optimization Made Easy",

abstract = "We introduce a Python package called RSOME for modeling a wide spectrum of robust and distributionally robust optimization problems. RSOME serves as an open-source framework for modeling various optimization problems subject to distributional ambiguity in a highly readable and mathematically intuitive manner. It is versatile and fits well in the open-source software community in the sense that (i) it is consistent with NumPy arrays in indexing and slicing and; (ii) together with the rich Python libraries for machine learning, data analysis, and visualization, it is easy to implement data-driven models; and (iii) it pro-vides convenient interfaces for users to switch and tune parameters among different solvers.{\textcopyright} 2023 INFORMS",

keywords = "(distributionally) robust optimization, algebraic modeling package, adaptive decision making, data-driven analytics",

author = "Zhi Chen and Peng Xiong",

year = "2023",

month = jul,

doi = "10.1287/ijoc.2023.1291",

language = "English",

volume = "35",

pages = "717--724",

journal = "INFORMS Journal on Computing",

issn = "1091-9856",

publisher = "Institute for Operations Research and the Management Sciences (INFORMS)",

number = "4",

}

TY - JOUR

T1 - RSOME in Python

T2 - An Open-Source Package for Robust Stochastic Optimization Made Easy

AU - Chen, Zhi

AU - Xiong, Peng

PY - 2023/7

Y1 - 2023/7

N2 - We introduce a Python package called RSOME for modeling a wide spectrum of robust and distributionally robust optimization problems. RSOME serves as an open-source framework for modeling various optimization problems subject to distributional ambiguity in a highly readable and mathematically intuitive manner. It is versatile and fits well in the open-source software community in the sense that (i) it is consistent with NumPy arrays in indexing and slicing and; (ii) together with the rich Python libraries for machine learning, data analysis, and visualization, it is easy to implement data-driven models; and (iii) it pro-vides convenient interfaces for users to switch and tune parameters among different solvers.© 2023 INFORMS

AB - We introduce a Python package called RSOME for modeling a wide spectrum of robust and distributionally robust optimization problems. RSOME serves as an open-source framework for modeling various optimization problems subject to distributional ambiguity in a highly readable and mathematically intuitive manner. It is versatile and fits well in the open-source software community in the sense that (i) it is consistent with NumPy arrays in indexing and slicing and; (ii) together with the rich Python libraries for machine learning, data analysis, and visualization, it is easy to implement data-driven models; and (iii) it pro-vides convenient interfaces for users to switch and tune parameters among different solvers.© 2023 INFORMS

KW - (distributionally) robust optimization

KW - algebraic modeling package

KW - adaptive decision making

KW - data-driven analytics

UR - http://www.scopus.com/inward/record.url?scp=85168795938&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85168795938&origin=recordpage

U2 - 10.1287/ijoc.2023.1291

DO - 10.1287/ijoc.2023.1291

M3 - RGC 21 - Publication in refereed journal

SN - 1091-9856

VL - 35

SP - 717

EP - 724

JO - INFORMS Journal on Computing

JF - INFORMS Journal on Computing

IS - 4

ER -

RSOME in Python: An Open-Source Package for Robust Stochastic Optimization Made Easy

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this