A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning: Principals, Recent Advances, and Applications

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 eva...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE signal processing magazine Ročník 37; číslo 5; s. 43 - 54
Hlavní autori: Liu, Sijia, Chen, Pin-Yu, Kailkhura, Bhavya, Zhang, Gaoyuan, Hero, Alfred O., Varshney, Pramod K.
Médium: Magazine Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.09.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Approximation error
Convergence
Estimation
Linear programming
Machine learning
Optimization
Signal processing
Signal processing algorithms
ISSN:1053-5888, 1558-0792
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1053-5888
1558-0792
DOI:10.1109/MSP.2020.3003837