A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
It serves as a primer for researchers and practitioners needing gradient-free optimization techniques, but it is incremental as a review paper.
The paper provides a comprehensive review of zeroth-order optimization, a gradient-free method used in signal processing and machine learning, covering its principles, convergence analysis, and applications like robustness evaluation and black-box model explanation.
Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning 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 solution update. In this paper, 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 models, and efficient online sensor management.