TY - JOUR
T1 - A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
T2 - Principals, Recent Advances, and Applications
AU - Liu, Sijia
AU - Chen, Pin Yu
AU - Kailkhura, Bhavya
AU - Zhang, Gaoyuan
AU - Hero, Alfred O.
AU - Varshney, Pramod K.
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning (ML) applications. It is used for solving optimization problems similarly to gradient-based methods. However, it does not require the gradient, using only function evaluations. Specifically, ZO optimization iteratively performs three major steps: gradient estimation, descent direction computation, and the solution update. In this article, we provide a comprehensive review of ZO optimization, with an emphasis on showing the underlying intuition, optimization principles, and recent advances in convergence analysis. Moreover, we demonstrate promising applications of ZO optimization, such as evaluating robustness and generating explanations from black-box deep learning (DL) models and efficient online sensor management.
AB - Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning (ML) applications. It is used for solving optimization problems similarly to gradient-based methods. However, it does not require the gradient, using only function evaluations. Specifically, ZO optimization iteratively performs three major steps: gradient estimation, descent direction computation, and the solution update. In this article, we provide a comprehensive review of ZO optimization, with an emphasis on showing the underlying intuition, optimization principles, and recent advances in convergence analysis. Moreover, we demonstrate promising applications of ZO optimization, such as evaluating robustness and generating explanations from black-box deep learning (DL) models and efficient online sensor management.
UR - http://www.scopus.com/inward/record.url?scp=85090963883&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090963883&partnerID=8YFLogxK
U2 - 10.1109/MSP.2020.3003837
DO - 10.1109/MSP.2020.3003837
M3 - Article
AN - SCOPUS:85090963883
SN - 1053-5888
VL - 37
SP - 43
EP - 54
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
IS - 5
M1 - 9186148
ER -