TY - JOUR
T1 - Nonconvex Min-Max Optimization
T2 - Applications, Challenges, and Recent Theoretical Advances
AU - Razaviyayn, Meisam
AU - Huang, Tianjian
AU - Lu, Songtao
AU - Nouiehed, Maher
AU - Sanjabi, Maziar
AU - Hong, Mingyi
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem that is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument that leads to a small objective value even for the worst-case function in the given class. Min-max optimization problems have recently become very popular in a wide range of signal and data processing applications, such as fair beamforming, training generative adversarial networks (GANs), and robust machine learning (ML), to just name a few.
AB - The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem that is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument that leads to a small objective value even for the worst-case function in the given class. Min-max optimization problems have recently become very popular in a wide range of signal and data processing applications, such as fair beamforming, training generative adversarial networks (GANs), and robust machine learning (ML), to just name a few.
UR - http://www.scopus.com/inward/record.url?scp=85090952537&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090952537&partnerID=8YFLogxK
U2 - 10.1109/MSP.2020.3003851
DO - 10.1109/MSP.2020.3003851
M3 - Article
AN - SCOPUS:85090952537
SN - 1053-5888
VL - 37
SP - 55
EP - 66
JO - IEEE Audio and Electroacoustics Newsletter
JF - IEEE Audio and Electroacoustics Newsletter
IS - 5
M1 - 9186144
ER -