eduzhai > Applied Sciences > Engineering >

A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning

  • Save

... pages left unread,continue reading

Document pages: 13 pages

Abstract: Zeroth-order (ZO) optimization is a subset of gradient-free optimization thatemerges in many signal processing and machine learning applications. It is usedfor 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: gradientestimation, descent direction computation, and solution update. In this paper,we provide a comprehensive review of ZO optimization, with an emphasis onshowing the underlying intuition, optimization principles and recent advancesin convergence analysis. Moreover, we demonstrate promising applications of ZOoptimization, such as evaluating robustness and generating explanations fromblack-box deep learning models, and efficient online sensor management.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×