The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
A variational perspective on accelerated methods in optimization
Open accessAbstract
Significance: Optimization problems arise naturally in statistical machine learning and other fields concerned with data analysis. The rapid growth in the scale and complexity of modern datasets has led to a focus on gradient-based methods and also on the class of accelerated methods, first proposed by Nesterov in 1983. Accelerated methods achieve faster convergence rates than gradient methods and indeed, under certain conditions, they achieve optimal rates. However, accelerated methods are not descent methods and remain a conceptual mystery. We propose a variational, continuous-time framework for understanding accelerated methods. We provide a systematic methodology for converting accelerated higher-order methods from continuous time to discrete time. Our work illuminates a class of dynamics that may be useful for designing better algorithms for optimization.
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 Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952
Introductory Lectures on Convex Optimization
Nesterov, Y. (2004) · Applied Optimization · doi:10.1007/978-1-4419-8853-9 · Cited by 2,698
A method for solving the convex programming problem with convergence rate O(1/k^2)
Nesterov, Y. E. (1983) · Доклады Академии наук · Cited by 2,662
Smooth minimization of non-smooth functions
Nesterov, Y. (2005) · Mathematical Programming · doi:10.1007/s10107-004-0552-5 · Cited by 2,455
Finite-time convergent gradient flows with applications to network consensus
Cortés, J. (2006) · Automatica · doi:10.1016/j.automatica.2006.06.015 · Cited by 818
Cubic regularization of Newton method and its global performance
Nesterov, Y., & Polyak, B. T. (2006) · Mathematical Programming · doi:10.1007/s10107-006-0706-8 · Cited by 781
Adaptive Restart for Accelerated Gradient Schemes
O’Donoghue, B., & Candès, E. (2015) · Foundations of Computational Mathematics · doi:10.1007/s10208-013-9150-3 · Cited by 642
Accelerated proximal gradient methods for nonconvex programming
Li, H., & Lin, Z. (2015) · neural information processing systems · Cited by 507
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
A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
Su, W., Boyd, S., & Candès, E. J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.01243 · Cited by 481
An optimal method for stochastic composite optimization
Lan, G. (2012) · Mathematical Programming · doi:10.1007/s10107-010-0434-y · Cited by 427 · cited 1×
“Introduced by Nesterov in 1983 [24] in the context of gradient descent, the acceleration idea has been extended to a wide range of other settings, including composite optimization [27, 33, 7], stochastic optimization [12, 18], nonconvex optimization [11, 21], and conic programming [19].”
BackgroundAnalysis and Design of Optimization Algorithms via Integral Quadratic Constraints
Lessard, L., Recht, B., & Packard, A. (2016) · SIAM Journal on Optimization · doi:10.1137/15m1009597 · Cited by 383
Linear Coupling: An Ultimate Unification of Gradient and Mirror DescentPreprint
Allen-Zhu, Z., & Orecchia, L. (2014) · arXiv (Cornell University) · doi:10.4230/lipics.itcs.2017.3 · Cited by 191
Accelerated mirror descent in continuous and discrete time
Krichene, W., Bayen, A. M., & Bartlett, P. L. (2015) · QUT ePrints (Queensland University of Technology) · Cited by 149
Lan, G., Lu, Z., & Monteiro, R. D. C. (2009) · Mathematical Programming · doi:10.1007/s10107-008-0261-6 · Cited by 147
Accelerated Gradient Methods for Stochastic Optimization and Online Learning
Hu, C., Pan, W., & Kwok, J. T.-Y. (2009) · Cited by 140
Hessian Riemannian Gradient Flows in Convex Programming
Alvarez, F., Bolte, J., & Brahic, O. (2004) · SIAM Journal on Control and Optimization · doi:10.1137/s0363012902419977 · Cited by 72
The Information Geometry of Mirror Descent
Raskutti, G., & Mukherjee, S. (2015) · IEEE Transactions on Information Theory · doi:10.1109/tit.2015.2388583 · Cited by 50
Cited by
An operator splitting approach for distributed generalized Nash equilibria computation
Yi, P., & Pavel, L. (2019) · Automatica · doi:10.1016/j.automatica.2019.01.008 · Cited by 271
Metadata
- Authors
- Wibisono, A., Wilson, A. C., & Jordan, M. I.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2016-11-09
- Volume
- 113
- Issue
- 47
- Pages
- E7351-E7358
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W2298465274
- Cited by
- 440
- References
- 18
- FWCI
- 34.03
- 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.