An optimal method for stochastic composite optimization
The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Recent advances in differential privacy for dynamic databases and time series data [143, 142, 97] have all assumed the existence of a trusted curator who can see raw data as they arrive online, and publish dynamically updated statistics.”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [97]
Citations
Cites
Bertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 11,726
Rockafellar, R. T. (1970) · Princeton University Press eBooks · doi:10.1515/9781400873173 · Cited by 10,801
A Stochastic Approximation Method
Robbins, H., & Monro, S. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729586 · Cited by 9,643 · cited 1×
“The classic SA method mimics the gradient descent method and goes back to the pioneering paper by Robbins and Monro [42].”
MethodA method for solving the convex programming problem with convergence rate O(1/k^2)
Nesterov, Y. E. (1983) · Доклады Академии наук · Cited by 6,318
Introductory Lectures on Convex Optimization: A Basic Course
Nesterov, Y. E. (2014) · Medical Entomology and Zoology · Cited by 3,557
Introductory Lectures on Convex Optimization
Nesterov, Y. (2004) · Applied Optimization · doi:10.1007/978-1-4419-8853-9 · Cited by 2,698
Bregman, L. M. (1967) · USSR Computational Mathematics and Mathematical Physics · doi:10.1016/0041-5553(67)90040-7 · Cited by 2,618
Weik, M. H. (2000) · Computer Science and Communications Dictionary · doi:10.1007/1-4020-0613-6_12436 · Cited by 2,570
Smooth minimization of non-smooth functions
Nesterov, Y. (2005) · Mathematical Programming · doi:10.1007/s10107-004-0552-5 · Cited by 2,455 · cited 11×
“Thirdly, while Nesterov’s optimal method and its variants [33, 35, 36 , 1, 20, 50] were designed for solving deterministic smooth convex optimization problems, the AC-SA algorithm described above is capable of solving non-smooth and stochastic convex optimization problems as well.”
BackgroundMethodInfluentialStochastic Programming: The State of the Art In Honor of George B. Dantzig
(2010) · International series in management science/operations research/International series in operations research & management science · doi:10.1007/978-1-4419-1642-6 · Cited by 2,239
Adaptive Algorithms and Stochastic Approximations
Benveniste, A., Métivier, M., & Priouret, P. (1990) · Springer eBooks · doi:10.1007/978-3-642-75894-2 · Cited by 2,006
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 · cited 1×
“Recent theoretical studies (cf., [16,45,46]) and numerical experiments (see e.g., [23,27,51]) show that the SAA method coupled with a good (deterministic) algorithm could be reasonably efficient for solving certain classes of two stage stochastic programming problems.”
MethodRobust 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-citationIntroduction to Stochastic Search and Optimization: Estimation, Simulation, and Control
Spall, J. C. (2003) · Wiley eBooks · doi:10.1002/0471722138 · Cited by 1,890
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 · cited 1×
“An important improvement of the SA method was developed by Polyak [40] and Polyak and Juditsky [41], where longer stepsizes were suggested with consequent averaging of the obtained iterates.”
MethodProblem complexity and method efficiency in optimization
(1984) · Mathematics and Computers in Simulation · doi:10.1016/0378-4754(84)90101-0 · Cited by 1,329 · cited 5×
“As a result, the rate of convergence of the the original mirror-descent SA algorithm with stepsize (27) will always be √ It should be noted that the mirror descent SA is a direct descendant of the mirror descent algorithm [31].”
InfluentialThe Existence of Probability Measures with Given Marginals
Strassen, V. (1965) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177700153 · Cited by 1,301 · cited 1×
“Observe that, under certain regularity assumptions [48,30], H̃(x, ξ) can be taken as a measurable subgradient of the function H̃(x, ξ) in (40).”
BackgroundGradient methods for minimizing composite objective functionPreprint
Nesterov, Y. E. (2007) · RePEc: Research Papers in Economics · Cited by 1,096
Mirror descent and nonlinear projected subgradient methods for convex optimization
Beck, A., & Teboulle, M. (2003) · Operations Research Letters · doi:10.1016/s0167-6377(02)00231-6 · Cited by 1,060 · cited 1×
“Nemirovski and Yudin [32] also developed the so-called mirror descent algorithm that can be advantageous over the subgradient descent method when X is not an Euclidean ball by using the prox-function (also called Bregman’s distance, which was studied by Bregman [9] and many others, see for example, [1, 2, 3 , 17, 49]…”
MethodINTRODUCTION TO STOCHASTIC SEARCH AND OPTIMIZATION: ESTIMATION, SIMULATION, AND CONTROL
Nowak, W. (2012) · Medical Entomology and Zoology · Cited by 1,033
Shapiro, A. (2003) · Handbooks in Operations Research and Management Science · doi:10.1016/s0927-0507(03)10006-0 · Cited by 916 · cited 2×
“Recent theoretical studies (cf., [16,45,46]) and numerical experiments (see e.g., [23,27,51]) show that the SAA method coupled with a good (deterministic) algorithm could be reasonably efficient for solving certain classes of two stage stochastic programming problems.”
MethodNESTA: A Fast and Accurate First-Order Method for Sparse Recovery
Becker, S., Bobin, J., & Candès, E. J. (2009) · Cited by 897
A method for unconstrained convex minimization problem with the rate of convergence o(1/k^2)
Nesterov, Y. E. (1983) · Medical Entomology and Zoology · Cited by 865
NESTA: A Fast and Accurate First-Order Method for Sparse Recovery
Becker, S., Bobin, J., & Candès, E. J. (2011) · SIAM Journal on Imaging Sciences · doi:10.1137/090756855 · Cited by 848 · cited 1×
“These first-order meth-ods were further studied in, for example, [1,8,26,28,37,38,50], and successfully used in sparse covariance selection, rank reduction in multivariate linear regression and compressed sensing, etc. (see for example, [3,9,24,25]).”
MethodPrimal-dual subgradient methods for convex problems
Nesterov, Y. (2009) · Mathematical Programming · doi:10.1007/s10107-007-0149-x · Cited by 835 · cited 2×
“Close techniques, based on subgradient averaging, have been proposed in Nesterov [35] and used in [12,14] to solve certain non-smooth stochastic convex optimization problems.”
MethodNemirovski, A. (2004) · SIAM Journal on Optimization · doi:10.1137/s1052623403425629 · Cited by 750 · cited 3×
“In contrast, our method, in addition to using the structure of the problem, only need to access the composite function itself; (iii) in [29,34,36] and other references mentioned above, only deterministic optimization problems have been considered.”
BackgroundMethodMonte Carlo bounding techniques for determining solution quality in stochastic programs
Mak, W.-K., Morton, D. P., & Wood, R. K. (1999) · Operations Research Letters · doi:10.1016/s0167-6377(98)00054-6 · Cited by 704 · cited 1×
“Recent theoretical studies (cf., [16,45,46]) and numerical experiments (see e.g., [23,27,51]) show that the SAA method coupled with a good (deterministic) algorithm could be reasonably efficient for solving certain classes of two stage stochastic programming problems.”
MethodVerweij, B., Ahmed, S., Kleywegt, A. J., Nemhauser, G. L., & Shapiro, A. (2003) · Computational Optimization and Applications · doi:10.1023/a:1021814225969 · Cited by 568
Solving Variational Inequalities with Stochastic Mirror-Prox Algorithm
Juditsky, A., Nemirovski, A. S., & Tauvel, C. (2011) · Stochastic Systems · doi:10.1287/10-ssy011 · Cited by 491
Gradient Convergence in Gradient methods with Errors
Bertsekas, D. P., & Tsitsiklis, J. N. (2000) · SIAM Journal on Optimization · doi:10.1137/s1052623497331063 · Cited by 437 · cited 1×
“It should be noted that the study on general smooth stochastic convex optimization (i.e., h(x) = 0 for every x2 X in (1) and > the strong convexity assumption on f seems quite limited in the literature (see [ 8 ] for the discussion on the simplest gradient methods with errors applied to this class of problems).”
BackgroundThe empirical behavior of sampling methods for stochastic programming
Linderoth, J., Shapiro, A., & Wright, S. (2006) · Annals of Operations Research · doi:10.1007/s10479-006-6169-8 · Cited by 425 · cited 1×
“Recent theoretical studies (cf., [16,45,46]) and numerical experiments (see e.g., [23,27,51]) show that the SAA method coupled with a good (deterministic) algorithm could be reasonably efficient for solving certain classes of two stage stochastic programming problems.”
MethodFirst-Order Methods for Sparse Covariance Selection
d'Aspremont, A., Banerjee, O., & El Ghaoui, L. (2008) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/060670985 · Cited by 343 · cited 1×
“These rst-order methods were further studied in, for example, [1, 39, 27, 10, 40, 50, 29], and successfully used in sparse covariance selection, rank reduction in multivariate linear regression and compressed sensing etc. (see, for example, [ 11 , 25, 26, 4]).”
MethodOn Complexity of Stochastic Programming Problems
Shapiro, A., & Nemirovski, A. (2006) · Applied Optimization · doi:10.1007/0-387-26771-9_4 · Cited by 301 · cited 1×
“Recent theoretical studies (cf., [16,45,46]) and numerical experiments (see e.g., [23,27,51]) show that the SAA method coupled with a good (deterministic) algorithm could be reasonably efficient for solving certain classes of two stage stochastic programming problems.”
MethodBregman Monotone Optimization Algorithms
Bauschke, H. H., Borwein, J. M., & Combettes, P. L. (2003) · SIAM Journal on Control and Optimization · doi:10.1137/s0363012902407120 · Cited by 281 · cited 2×
“…the so-called mirror descent algorithm that can be advantageous over the subgradient descent method when X is not an Euclidean ball by using a prox-function (also called Bregman’s distance, which was studied by Bregman [7] and many others, see for example, [1,2,15,49] and references therein).”
Backgroundstochastic quasigradient methods and their application to system optimization†
Ermoliev, Y. (1983) · Stochastics · doi:10.1080/17442508308833246 · Cited by 280 · cited 1×
“Since then stochastic approximation algorithms became widely used in stochastic optimization (see e.g., [5,10,11,17,39,44,47] and references therein).”
MethodInterior Gradient and Proximal Methods for Convex and Conic Optimization
Auslender, A., & Teboulle, M. (2006) · SIAM Journal on Optimization · doi:10.1137/s1052623403427823 · Cited by 269 · cited 6×
“In particular, Auslender and Teboule [1] give a more geometrically transparent definition for this notion.”
BackgroundMethodInfluentialOptimization of Stochastic Models
Pflug, G. C. (1996) · Kluwer international series in engineering and computer science · doi:10.1007/978-1-4613-1449-3 · Cited by 259 · cited 1×
“Since then stochastic approximation algorithms became widely used in stochastic optimization (see e.g., [5,10,11,17,39,44,47] and references therein).”
MethodProximal Minimization Methods with Generalized Bregman Functions
Kiwiel, K. C. (1997) · SIAM Journal on Control and Optimization · doi:10.1137/s0363012995281742 · Cited by 236 · cited 2×
“…the so-called mirror descent algorithm that can be advantageous over the subgradient descent method when X is not an Euclidean ball by using a prox-function (also called Bregman’s distance, which was studied by Bregman [7] and many others, see for example, [1,2,15,49] and references therein).”
BackgroundOptimization of Stochastic Models: The Interface Between Simulation and Optimization
Orman, A. J., & Pflug, G. C. (1998) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2600016 · Cited by 214
Convergence of Proximal-Like Algorithms
Teboulle, M. (1997) · SIAM Journal on Optimization · doi:10.1137/s1052623495292130 · Cited by 169 · cited 2×
“…the so-called mirror descent algorithm that can be advantageous over the subgradient descent method when X is not an Euclidean ball by using a prox-function (also called Bregman’s distance, which was studied by Bregman [7] and many others, see for example, [1,2,15,49] and references therein).”
BackgroundSmooth Optimization with Approximate Gradient
d'Aspremont, A. (2008) · SIAM Journal on Optimization · doi:10.1137/060676386 · Cited by 168 · cited 1×
“These first-order methods were further studied in, for example, [1,8,26,28,37,38,50], and successfully used in sparse covariance selection, rank reduction in multivariate linear regression and compressed sensing, etc.”
MethodA proximal method for composite minimization
Lewis, A. S., & Wright, S. J. (2016) · Mathematical Programming · doi:10.1007/s10107-015-0943-9 · Cited by 167
On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean
Monteiro, R. D. C., & Svaiter, B. F. (2010) · SIAM Journal on Optimization · doi:10.1137/090753127 · Cited by 153 · cited 1×
“These first-order methods were further studied in, for example, [1,8,26,28,37,38,50], and successfully used in sparse covariance selection, rank reduction in multivariate linear regression and compressed sensing, etc.”
MethodValidation 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 153
Self-citationLan, G., Lu, Z., & Monteiro, R. D. C. (2009) · Mathematical Programming · doi:10.1007/s10107-008-0261-6 · Cited by 147
Self-citationSmoothing Technique and its Applications in Semidefinite Optimization
Nesterov, Y. E. (2006) · Mathematical Programming · doi:10.1007/s10107-006-0001-8 · Cited by 140 · cited 3×
“[33, 1, 20] and [50, Section 3]), or 1-memory methods where the gradient information from all previous iterates is used (cf. [36, 39 ] and [50, Section 4]).”
BackgroundMethodInfluentialJuditsky, A., Rigollet, P., & Tsybakov, A. B. (2008) · The Annals of Statistics · doi:10.1214/07-aos546 · Cited by 139 · cited 1×
“Close techniques, based on subgradient averaging, have been proposed in Nesterov [35] and used in [12,14] to solve certain non-smooth stochastic convex optimization problems.”
MethodIteration-complexity of first-order augmented Lagrangian methods for convex programming
Lan, G., & Monteiro, R. D. C. (2015) · Mathematical Programming · doi:10.1007/s10107-015-0861-x · Cited by 115
Self-citationSmooth Optimization Approach for Sparse Covariance Selection
Lu, Z. (2009) · SIAM Journal on Optimization · doi:10.1137/070695915 · Cited by 105
Non-euclidean restricted memory level method for large-scale convex optimization
Ben‐Tal, A., & Nemirovski, A. S. (2004) · Mathematical Programming · doi:10.1007/s10107-004-0553-4 · Cited by 100 · cited 1×
“…∂φ( x ) consists of all vectors g , if any, such that there exists With this definition, it is well-known (see for example, Ben-Tal and Nemirovksi [4]) that, if a convex function φ : X → R is Lipschitz continuous, with constant M , with respect to a norm (cid:6) · (cid:6) , then the set ∂φ( x )…”
BackgroundRecursive 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
Iteration-complexity of first-order penalty methods for convex programming
Lan, G., & Monteiro, R. D. C. (2012) · Mathematical Programming · doi:10.1007/s10107-012-0588-x · Cited by 68
Self-citationLu, Z., Monteiro, R. D. C., & Yuan, M. (2010) · Mathematical Programming · doi:10.1007/s10107-010-0350-1 · Cited by 58
Wessels, J. S. (1967) · Statistica Neerlandica · doi:10.1111/j.1467-9574.1967.tb00544.x · Cited by 49
Ruszczyński, A., & Syski, W. (1986) · Mathematical programming studies · doi:10.1007/bfb0121128 · Cited by 42 · cited 1×
“Since then stochastic approximation algorithms became widely used in stochastic optimization (see e.g., [5,10,11,17,39,44,47] and references therein).”
MethodNonstationary stochastic programming problems
Gaivoronskii, A. A. (1979) · Cybernetics and Systems Analysis · doi:10.1007/bf01069841 · Cited by 38 · cited 1×
“Since then stochastic approximation algorithms became widely used in stochastic optimization (see e.g., [5,10,11,17,39,44,47] and references therein).”
MethodLarge-scale semidefinite programming via a saddle point Mirror-Prox algorithm
Lu, Z., Nemirovski, A. S., & Monteiro, R. D. C. (2006) · Mathematical Programming · doi:10.1007/s10107-006-0031-2 · Cited by 28 · cited 1×
“These first-order meth-ods were further studied in, for example, [1,8,26,28,37,38,50], and successfully used in sparse covariance selection, rank reduction in multivariate linear regression and compressed sensing, etc. (see for example, [3,9,24,25]).”
Method
Research works printed but not linked: 4
- Kushner H., Yin J., Shapiro G.: Approximation and Recursive Algorithms and Applications, vol. 35 of Applications of Mathematics. Springer, New York (2003)
- Peña J.: Nash equilibria computation via smoothing techniques. Optima 78, 12–13 (2008)
- Polyak B.T.: New stochastic approximation type procedures. Automat. i Telemekh 7, 98–107 (1990)
- Tseng P.: On Accelerated Proximal Gradient Methods for Convex-Concave Optimization, Manuscript. University of Washington, Seattle (May 2008)
Cited by
(2010) · Cited by 8,261
Advances and Open Problems in Federated Learning
Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.04977 · Cited by 7,857
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
“[49] J. Wang, A. Sahu, G. Joshi, and S. Kar, “MATCHA: Speeding up decentralized SGD via matching decomposition sampling,” Preprint, May 2019.”
MethodInfluential(2013) · Cited by 3,740
Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
Ghadimi, S., & Lan, G. (2013) · SIAM Journal on Optimization · doi:10.1137/120880811 · Cited by 1,034
Self-citation
Metadata
- Authors
- Lan, G.
- Affiliations
- University of Florida (US)
- Corresponding author
- Lan, Guanghui
- ORCID
- Lan, Guanghui
- Venue
- Mathematical Programming
- Published
- 2011-01-01
- Volume
- 133
- Issue
- 1-2
- Pages
- 365-397
- ISSN
- 0025-5610 (ISSN-L)
- 1436-4646
- OpenAlex
- W2024484010
- Cited by
- 427
- References
- 55
- Citations by year
- 2026: 13 · 2025: 14 · 2024: 20 · 2023: 23 · 2022: 25 · 2021: 47 · 2020: 45 · 2019: 40 · 2018: 40 · 2017: 43 · 2016: 30 · 2015: 20 · 2014: 29 · 2013: 14 · 2012: 11
- FWCI
- 10.80
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Mathematical Programming (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
- Physical Sciences › Mathematics › Numerical Analysis › Advanced Optimization Algorithms Research
- Keywords
- convex optimization, mirror descent, stochastic approximation, convergence rate, lower bounds, nonsmooth optimization, stochastic programming, optimal algorithms
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.