A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning: Principals, Recent Advances, and Applications
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
A Simplex Method for Function Minimization
Nelder, J. A., & Mead, R. (1965) · The Computer Journal · doi:10.1093/comjnl/7.4.308 · Cited by 28,905
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 1×
“, model-agnostic meta-learning [90], ZO optimization could help to overcome the derivative bottleneck.”
BackgroundPractical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
Genetic Algorithms and Machine Learning
Goldberg, D. E., & Holland, J. H. (1988) · Machine Learning · doi:10.1023/a:1022602019183 · Cited by 3,193 · cited 1×
“Evolutionary optimization is another class of generic population-based meta heuristic DFO algorithms, and includes particle swarm optimization methods [12] and genetic algorithms [13].”
MethodReinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · cited 2×
“Model-free policy search updates the parameters such that trajectories with higher reward are more likely to be obtained when following the updated policy [77].”
BackgroundMethodMultivariate stochastic approximation using a simultaneous perturbation gradient approximation
Spall, J. C. (1992) · IEEE Transactions on Automatic Control · doi:10.1109/9.119632 · Cited by 2,283
Powell, M. J. D. (1994) · Advances in Optimization and Numerical Analysis · doi:10.1007/978-94-015-8330-5_4 · Cited by 1,369
Derivative-free optimization: a review of algorithms and comparison of software implementations
Rios, L. M., & Sahinidis, N. V. (2013) · Journal of Global Optimization · doi:10.1007/s10898-012-9951-y · Cited by 1,276
Decision-based adversarial attacks: Reliable attacks against black-box machine learning models
Brendel, W., Rauber, J., & Bethge, M. (2017) · arXiv · doi:10.48550/arxiv.1712.04248 · Cited by 1,018
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
Cheng, M., Le, T., Chen, P.-Y., Yi, J., Zhang, H., & Hsieh, C.-J. (2018) · arXiv · doi:10.48550/arxiv.1807.04457 · Cited by 269
Self-citationBandit Convex Optimization for Scalable and Dynamic IoT Management
Chen, T., & Giannakis, G. B. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2839563 · Cited by 139 · cited 1×
“Online sensor management provides an example of such a scenario [27], [72].”
Background
Cited by
On the Convergence of Zeroth-Order Federated Tuning for Large Language Models
Ling, Z., Chen, D., Yao, L., Li, Y., & Shen, Y. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671865 · Cited by 21
“With this insight, [39] identified the bound of loss descent at each step of centralized ZOO, which is partially influenced by 𝑟 : Lemma 2.3.”
BackgroundInfluential
Metadata
- Authors
- Liu, S., Chen, P.-Y., Kailkhura, B., Zhang, G., Hero, A. O., & Varshney, P. K.
- Venue
- IEEE Signal Processing Magazine
- Published
- 2020-09
- Volume
- 37
- Issue
- 5
- Pages
- 43-54
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W3083021344
- Cited by
- 185
- References
- 16
- FWCI
- 6.54
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.