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

Abstract

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.

IEEE Signal Processing Magazine

References in corpus (7)

• Practical Bayesian Optimization of Machine Learning Algorithms
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
• Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources
• Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective
• Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
• Zeroth-order Asynchronous Doubly Stochastic Algorithm with Variance Reduction

Cited by in corpus (3)

• Don't Forget to Sign the Gradients!
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
• Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples