A one-measurement form of simultaneous perturbation stochastic approximation
Open accessThe DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index.
Abstract
The simultaneous perturbation stochastic approximation (SPSA) algorithm has proven very effective for difficult multivariate optimization problems where it is not possible to obtain direct gradient information. As discussed to date, SPSA is based on a highly efficient gradient approximation requiring only two measurements of the loss function independent of the number of parameters being estimated. This note presents a form of SPSA that requires only one function measurement (for any dimension). Theory is presented that identifies the class of problems for which this one-measurement form will be asymptotically superior to the standard two-measurement form.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Techniques exist to reduce them to two-body terms by adding ancilla qubits and encoding the correct couplings in the lowest eigenstate of a different Hamiltonian, which is commonly called gadgetization 42,208,372-374 .”
From Quantum Chemistry in the Age of Quantum Computing (2019) · cites this paper as [374]
Experimental — accuracy not yet measured
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
Multivariate 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
Self-citationAcceleration of Stochastic Approximation by Averaging
Polyak, B. T., & Juditsky, A. B. (1992) · SIAM Journal on Control and Optimization · doi:10.1137/0330046 · Cited by 1,827
Implementation of the simultaneous perturbation algorithm for stochastic optimization
Spall, J. C. (1998) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.705889 · Cited by 797
Self-citation(2005) · Interdisciplinary Mathematical Sciences · doi:10.1142/9789812701039_0003 · Cited by 611
Borkar, V. S. (2008) · Texts and Readings in Mathematics · doi:10.1007/978-93-86279-38-5 · Cited by 561
Optimizing Methods in Statistics
(1971) · Elsevier eBooks · doi:10.1016/c2013-0-11433-x · Cited by 436
Handbook of Sequential Analysis
Ziegel, E. R., Ghosh, B., & Sen, P. (1994) · Technometrics · doi:10.2307/1269396 · Cited by 392
On Asymptotic Normality in Stochastic Approximation
Fabian, V. (1968) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177698258 · Cited by 312 · cited 2×
“(1992), which were based on an asymptotic distribution theory in Fabian (1968) (the author is unaware of any formal distribution theory for the finite-sample case).”
BackgroundMethodEfficient Estimations from a Slowly Convergent Robbins-Monro Process
Ruppert, D. (1988) · eCommons (Cornell University) · Cited by 277
Optimizing Methods in Statistics
Williams, T. M., & Rustagi, J. S. (1981) · The Journal of the Operational Research Society · doi:10.2307/2581546 · Cited by 170
Research works printed but not linked: 2
- Ruppert, 1983, Kiefer-Wolfowitz procedure, Vol. 4, 379
- Spall, J. C. and J. A. Cristion (1994). Nonlinear adaptive control using neural networks: estimation based on a smoothed form of simultaneous perturbation gradient approximation. Statistica Sinica, 4, l-27.
Cited by
Supervised learning with quantum-enhanced feature spaces
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019) · Nature · doi:10.1038/s41586-019-0980-2 · Cited by 2,572
“We have found that Spall’s SPSA [23, 24] stochastic gradient decent algorithm performs well in the noisy experimental setting.”
BackgroundQuantum Chemistry in the Age of Quantum Computing
Cao, Y., Romero, J., Olson, J. P., Degroote, M., Johnson, P. D., Kieferová, M., Kivlichan, I. D., Menke, T., Peropadre, B., Sawaya, N. P. D., et al. (2019) · Chemical Reviews · doi:10.1021/acs.chemrev.8b00803 · Cited by 1,560
Parameterized quantum circuits as machine learning models
Benedetti, M., Lloyd, E., Sack, S., & Fiorentini, M. (2019) · Quantum Science and Technology · doi:10.1088/2058-9565/ab4eb5 · Cited by 1,144
“[41] James C Spall, “A one-measurement form of simultaneous perturbation stochastic approximation,” Automatica 33, 109–112 (1997).”
BackgroundImplementation of the simultaneous perturbation algorithm for stochastic optimization
Spall, J. C. (1998) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.705889 · Cited by 797
Self-citationQuantum optimization using variational algorithms on near-term quantum devices
Moll, N., Barkoutsos, P., Bishop, L. S., Chow, J. M., Cross, A., Egger, D. J., Filipp, S., Fuhrer, A., Gambetta, J. M., Ganzhorn, M., et al. (2018) · Quantum Science and Technology · doi:10.1088/2058-9565/aab822 · Cited by 744
“second derivatives helps achieve faster convergence [93]. In contrast, additional savings in time overhead in SPSA optimizations that rely on just one evaluation of the cost function per update step [94] could further improve the performance in large-scale quantum problems where sampling is particularly dicult. While…”
Background
Metadata
- Authors
- Spall, J. C.
- Affiliations
- Johns Hopkins University Applied Physics Laboratory (US)
- Corresponding author
- Spall, James C.
- ORCID
- Spall, James C.
- Venue
- Automatica
- Publisher
- Elsevier BV
- Published
- 1997-01
- Volume
- 33
- Issue
- 1
- Pages
- 109-112
- ISSN
- 0005-1098 (ISSN-L)
- OpenAlex
- W2012117977
- Cited by
- 254
- References
- 27
- Citations by year
- 2026: 7 · 2025: 22 · 2024: 16 · 2023: 19 · 2022: 14 · 2021: 21 · 2020: 13 · 2019: 8 · 2018: 15 · 2017: 4 · 2016: 8 · 2015: 7 · 2014: 5 · 2013: 4 · 2012: 7
- FWCI
- 4.56
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc-nd
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0/ (vor, 501 d)
- Locations
- Automatica (publishedVersion, cc-by-nc-nd)
- Funders
- U.S. Navy
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Simulation Techniques and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Physical Sciences › Engineering › Control and Systems Engineering › Adaptive Dynamic Programming Control
- Keywords
- simultaneous perturbation stochastic approximation, gradient approximation, multivariate optimization, derivative-free optimization, asymptotic performance, parameter estimation
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A one-measurement form of simultaneous perturbation stochastic approximation. https://app.cochat.ai/papers/10.1016/s0005-1098(96)00149-5
- The paper
- Spall, J. C. (1997). A one-measurement form of simultaneous perturbation stochastic approximation. Automatica. https://doi.org/10.1016/s0005-1098(96)00149-5
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.