A primer on zeroth-order optimization in signal processing and machine learning: Principals, recent advances, and applications

S Liu, PY Chen, B Kailkhura, G Zhang… - IEEE Signal …, 2020‏ - ieeexplore.ieee.org
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 …

SF-FWA: A self-adaptive fast fireworks algorithm for effective large-scale optimization

M Chen, Y Tan - Swarm and Evolutionary Computation, 2023‏ - Elsevier
Computationally efficient algorithms for large-scale black-box optimization have become
increasingly important in recent years due to the growing complexity of engineering and …

Simultaneously optimizing perturbations and positions for black-box adversarial patch attacks

X Wei, Y Guo, J Yu, B Zhang - IEEE transactions on pattern …, 2022‏ - ieeexplore.ieee.org
Adversarial patch is an important form of real-world adversarial attack that brings serious
risks to the robustness of deep neural networks. Previous methods generate adversarial …

Revisiting zeroth-order optimization for memory-efficient llm fine-tuning: A benchmark

Y Zhang, P Li, J Hong, J Li, Y Zhang, W Zheng… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained
Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has …

Derivative-free reinforcement learning: A review

H Qian, Y Yu - Frontiers of Computer Science, 2021‏ - Springer
Reinforcement learning is about learning agent models that make the best sequential
decisions in unknown environments. In an unknown environment, the agent needs to …

Gradient-free methods for deterministic and stochastic nonsmooth nonconvex optimization

T Lin, Z Zheng, M Jordan - Advances in Neural Information …, 2022‏ - proceedings.neurips.cc
Nonsmooth nonconvex optimization problems broadly emerge in machine learning and
business decision making, whereas two core challenges impede the development of …

Sparse-rs: a versatile framework for query-efficient sparse black-box adversarial attacks

F Croce, M Andriushchenko, ND Singh… - Proceedings of the …, 2022‏ - ojs.aaai.org
We propose a versatile framework based on random search, Sparse-RS, for score-based
sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on …

Adaptive and communication-efficient zeroth-order optimization for distributed internet of things

Q Dang, S Yang, Q Liu, J Ruan - IEEE Internet of Things …, 2024‏ - ieeexplore.ieee.org
This article addresses the optimization problem of zeroth-order in a distributed setting,
where the gradient information is not available in the edge Internet of Things (IoT) clients …

Adaptive momentum variance for attention-guided sparse adversarial attacks

C Li, W Yao, H Wang, T Jiang - Pattern Recognition, 2023‏ - Elsevier
The phenomenon that deep neural networks are vulnerable to adversarial examples has
been found for several years. Under the black-box setting, transfer-based methods usually …

Optimizing molecules using efficient queries from property evaluations

SC Hoffman, V Chenthamarakshan… - Nature Machine …, 2022‏ - nature.com
Abstract Machine learning-based methods have shown potential for optimizing existing
molecules with more desirable properties, a critical step towards accelerating new chemical …