The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
Open accessAbstract
Classical stochastic gradient methods are well suited for minimizing expected-value objective functions. However, they do not apply to the minimization of a nonlinear function involving expected values or a composition of two expected-value functions, i.e., the problem minxEvfv(Ew[gw(x)]).\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\min _x \mathbf{E}_v\left[ f_v\big (\mathbf{E}_w [g_w(x)]\big ) \right] .$$\end{document} In order to solve this stochastic composition problem, we propose a class of stochastic compositional gradient descent (SCGD) algorithms that can be viewed as stochastic versions of quasi-gradient method. SCGD update the solutions based on noisy sample gradients of fv,gw\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$f_v,g_{w}$$\end{document} and use an auxiliary variable to track the unknown quantity Ewgw(x)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathbf{E}_w\left[ g_w(x)\right] $$\end{document}. We prove that the SCGD converge almost surely to an optimal solution for convex optimization problems, as long as such a solution exists. The convergence involves the interplay of two iterations with different time scales. For nonsmooth convex problems, the SCGD achieves a convergence rate of O(k-1/4)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {O}(k^{-1/4})$$\end{document} in the general case and O(k-2/3)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {O}(k^{-2/3})$$\end{document} in the strongly convex case, after taking k samples. For smooth convex problems, the SCGD can be accelerated to converge at a rate of O(k-2/7)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {O}(k^{-2/7})$$\end{document} in the general case and O(k-4/5)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {O}(k^{-4/5})$$\end{document} in the strongly convex case. For nonconvex problems, we prove that any limit point generated by SCGD is a stationary point, for which we also provide the convergence rate analysis. Indeed, the stochastic setting where one wants to optimize compositions of expected-value functions is very common in practice. The proposed SCGD methods find wide applications in learning, estimation, dynamic programming, etc.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Acceleration 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
Model selection and estimation in the Gaussian graphical model
Yuan, M., & Lin, Y. (2007) · Biometrika · doi:10.1093/biomet/asm018 · Cited by 1,627
Cited by
AUC Maximization in the Era of Big Data and AI: A Survey
Yang, T., & Ying, Y. (2023) · ACM Computing Surveys · doi:10.1145/3554729 · Cited by 323
Stochastic Model-Based Minimization of Weakly Convex Functions
Davis, D., & Drusvyatskiy, D. (2019) · SIAM Journal on Optimization · doi:10.1137/18m1178244 · Cited by 258
FFS-VA: A Fast Filtering System for Large-scale Video Analytics
Zhang, C., Cao, Q., Jiang, H., Zhang, W., Li, J., & Yao, J. (2018) · Proceedings of the 47th International Conference on Parallel Processing · doi:10.1145/3225058.3225103 · Cited by 16
Fast Stochastic Recursive Momentum Methods for Imbalanced Data Mining
Wu, X., Huang, F., & Huang, H. (2022) · 2022 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm54844.2022.00068 · Cited by 7
Metadata
- Authors
- Wang, M., Fang, E. X., & Liu, H.
- Venue
- Mathematical Programming
- Published
- 2016-05-07
- Volume
- 161
- Issue
- 1-2
- Pages
- 419-449
- ISSN
- 0025-5610 (ISSN-L)
- 1436-4646
- OpenAlex
- W1494085563
- Cited by
- 178
- References
- 2
- FWCI
- 11.34
- Type
- journal article
- Language
- en
- Open access
- green
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: Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions. https://app.cochat.ai/papers/10.1007/s10107-016-1017-3
- The paper
- Wang, M., Fang, E. X., & Liu, H. (2017). Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions. Mathematical Programming. https://doi.org/10.1007/s10107-016-1017-3
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.