The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
Open accessAbstract
In this paper, we introduce a new stochastic approximation type algorithm, namely, the randomized stochastic gradient (RSG) method, for solving an important class of nonlinear (possibly nonconvex) stochastic programming problems. We establish the complexity of this method for computing an approximate stationary point of a nonlinear programming problem. We also show that this method possesses a nearly optimal rate of convergence if the problem is convex. We discuss a variant of the algorithm which consists of applying a postoptimization phase to evaluate a short list of solutions generated by several independent runs of the RSG method, and we show that such modification allows us to improve significantly the large-deviation properties of the algorithm. These methods are then specialized for solving a class of simulation-based optimization problems in which only stochastic zeroth-order information is available.
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
A Stochastic Approximation Method
Robbins, H., & Monro, S. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729586 · Cited by 9,643
Online dictionary learning for sparse coding
Mairal, J., Bach, F., Ponce, J., & Sapiro, G. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553463 · Cited by 2,114
The Sample Average Approximation Method for Stochastic Discrete Optimization
Kleywegt, A. J., Shapiro, A., & Homem-de-Mello, T. (2002) · SIAM Journal on Optimization · doi:10.1137/s1052623499363220 · Cited by 1,983
Robust Stochastic Approximation Approach to Stochastic Programming
Nemirovski, A., Juditsky, A., Lan, G., & Shapiro, A. (2009) · SIAM Journal on Optimization · doi:10.1137/070704277 · Cited by 1,945
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
Primal-dual subgradient methods for convex problems
Nesterov, Y. (2009) · Mathematical Programming · doi:10.1007/s10107-007-0149-x · Cited by 835
Feature Article: Optimization for simulation: Theory vs. Practice
Fu, M. C. (2002) · INFORMS Journal on Computing · doi:10.1287/ijoc.14.3.192.113 · Cited by 742
An optimal method for stochastic composite optimization
Lan, G. (2012) · Mathematical Programming · doi:10.1007/s10107-010-0434-y · Cited by 427
Self-citationAsymptotic Distribution of Stochastic Approximation Procedures
Sacks, J. (1958) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177706619 · Cited by 368
On a Stochastic Approximation Method
Chung, K. L. (1954) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177728716 · Cited by 363
Ghadimi, S., & Lan, G. (2012) · SIAM Journal on Optimization · doi:10.1137/110848864 · Cited by 269
Self-citationA review of simulation optimization techniques
Andradottir, S. (2002) · 1998 Winter Simulation Conference. Proceedings (Cat. No.98CH36274) · doi:10.1109/wsc.1998.744910 · Cited by 204
Randomized smoothing for stochastic optimizationPreprint
Duchi, J. C., & Wainwright, M. J. (2016) · Cited by 188
Recursive Trust-Region Methods for Multiscale Nonlinear Optimization
Gratton, S., Sartenaer, A., & Toint, P. L. (2008) · SIAM Journal on Optimization · doi:10.1137/050623012 · Cited by 174
Ghadimi, S., & Lan, G. (2013) · SIAM Journal on Optimization · doi:10.1137/110848876 · Cited by 167
Self-citationJuditsky, A., Rigollet, P., & Tsybakov, A. B. (2008) · The Annals of Statistics · doi:10.1214/07-aos546 · Cited by 139
Validation analysis of mirror descent stochastic approximation method
Lan, G., Nemirovski, A. S., & Shapiro, A. (2011) · Mathematical Programming · doi:10.1007/s10107-011-0442-6 · Cited by 121
Self-citationOn stochastic gradient and subgradient methods with adaptive steplength sequences
Yousefian, F., Nedić, A., & Shanbhag, U. V. (2011) · Automatica · doi:10.1016/j.automatica.2011.09.043 · Cited by 118
Recursive Aggregation of Estimators by the Mirror Descent Algorithm with Averaging
Juditsky, A., Nazin, A., Tsybakov, A. B., & Vayatis, N. (2005) · Problems of Information Transmission · doi:10.1007/s11122-006-0005-2 · Cited by 77
Smoothing and worst-case complexity for direct-search methods in nonsmooth optimization
Garmanjani, R., & Vicente, L. N. (2012) · IMA Journal of Numerical Analysis · doi:10.1093/imanum/drs027 · Cited by 47
Cited by
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
“…for very small ǫ , if we replace B ǫ with its upper-bound in Remark 4.0.1 and choose µ large enough, then the iteration complexity of FedProx when the subproblems are solved exactly and F k ( ) ’s are convex would be O ( L ∆ ǫ + L ∆ σ 2 ǫ 2 ) which is the same as SGD Ghadimi & Lan (2013).”
BackgroundInfluentialChen, P.-Y., Zhang, H., Sharma, Y., Yi, J., & Hsieh, C.-J. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140448 · Cited by 1,656
Averaging Weights Leads to Wider Optima and Better Generalization
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., & Wilson, A. G. (2018) · arXiv · doi:10.48550/arxiv.1803.05407 · Cited by 1,409
Yu, H., Yang, S., & Zhu, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015693 · Cited by 497
Accelerated gradient methods for nonconvex nonlinear and stochastic programming
Ghadimi, S., & Lan, G. (2016) · Mathematical Programming · doi:10.1007/s10107-015-0871-8 · Cited by 487
Self-citation
Metadata
- Authors
- Ghadimi, S., & Lan, G.
- Venue
- SIAM Journal on Optimization
- Published
- 2013-01
- Volume
- 23
- Issue
- 4
- Pages
- 2341-2368
- ISSN
- 1052-6234 (ISSN-L)
- 1095-7189
- OpenAlex
- W2963470657
- Cited by
- 1,034
- References
- 20
- FWCI
- 15.83
- 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
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.