Harnessing smoothness to accelerate distributed optimization
The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Abstract
There has been a growing effort in studying the distributed optimization problem over a network. The objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. Literature has developed consensus-based distributed (sub)gradient descent (DGD) methods and has shown that they have the same convergence rate O(log t/√t) as the centralized (sub)gradient methods (CGD) when the function is convex but possibly nonsmooth. However, when the function is convex and smooth, under the framework of DGD, it is unclear how to harness the smoothness to obtain a faster convergence rate comparable to CGD's convergence rate. In this paper, we propose a distributed algorithm that, despite using the same amount of communication per iteration as DGD, can effectively harnesses the function smoothness and converge to the optimum with a rate of O(1/t). If the objective function is further strongly convex, our algorithm has a linear convergence rate. Both rates match the convergence rate of CGD. The key step in our algorithm is a novel gradient estimation scheme that uses history information to achieve fast and accurate estimation of the average gradient. To motivate the necessity of history information, we also show that it is impossible for a class of distributed algorithms like DGD to achieve a linear convergence rate without using history information even if the objective function is strongly convex and smooth.
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
“However, none of the papers mentioned in this paragraph provide a theoretical analysis for strongly convex optimization problems over time-varying graphs , which is the goal of this paper.”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [52]
In the citing paper
“Finally, we note that reference [52], appearing simultaneously with this work, also proposed a method for distributed optimization based on gradient differences.”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [52]
Citations
Cites
Bertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 11,726
Consensus and Cooperation in Networked Multi-Agent Systems
Olfati-Saber, R., Fax, J. A., & Murray, R. M. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.887293 · Cited by 10,522 · cited 1×
“2The selection of the consensus weights is an intensely studied problem, see [23], [24].”
BackgroundErdős, P., & Rényi, A. (2022) · Publicationes Mathematicae Debrecen · doi:10.5486/pmd.1959.6.3-4.12 · Cited by 5,337
Parallel and Distributed Computation: Numerical Methods
Bertsekas, D. P., & Tsitsiklis, J. N. (1989) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 5,293
Distributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719 · cited 4×
“, [6], [8]–[13], [16]– [18], [20], [21], that combine a consensus algorithm and a first order optimization algorithm.”
BackgroundMethodInfluentialMatrix Analysis and Applied Linear Algebra
Meyer, C. (2000) · doi:10.1137/1.9780898719512 · Cited by 3,565
Introductory Lectures on Convex Optimization: A Basic Course
Nesterov, Y. E. (2014) · Medical Entomology and Zoology · Cited by 3,557
Matrix analysis and applied linear algebra
(2001) · Choice Reviews Online · doi:10.5860/choice.38-5065 · Cited by 3,300
Parlar, M. (2000) · Interactive Operations Research with Maple · doi:10.1007/978-1-4612-1356-7_5 · Cited by 1,741
EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
Shi, W., Ling, Q., Wu, G., & Yin, W. (2015) · SIAM Journal on Optimization · doi:10.1137/14096668x · Cited by 1,261
Research works printed but not linked: 1
- 2012, Logistic Regression
Cited by
Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
Nedić, A., Olshevsky, A., & Shi, W. (2017) · SIAM Journal on Optimization · doi:10.1137/16m1084316 · Cited by 1,069
“Finally, we note that reference [52], appearing simultaneously with this work, also proposed a method for distributed optimization based on gradient differences.”
MethodHarnessing Smoothness to Accelerate Distributed Optimization
Qu, G., & Li, N. (2018) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2698261 · Cited by 565
Self-citationNetwork Topology and Communication-Computation Tradeoffs in Decentralized Optimization
Nedic, A., Olshevsky, A., & Rabbat, M. G. (2018) · Proceedings of the IEEE · doi:10.1109/jproc.2018.2817461 · Cited by 534
Li, Z., Shi, W., & Yan, M. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2926022 · Cited by 244
A Linear Algorithm for Optimization Over Directed Graphs With Geometric Convergence
Xin, R., & Khan, U. A. (2018) · IEEE Control Systems Letters · doi:10.1109/lcsys.2018.2834316 · Cited by 243
Metadata
- Authors
- Qu, G., & Li, N.
- Affiliations
- Harvard University (US)
- ORCID
- Venue
- 2016 IEEE 55th Conference on Decision and Control (CDC)
- Publisher
- IEEE
- Published
- 2016-12
- Pages
- 159-166
- ISSN
- 0191-2216 (ISSN-L)
- OpenAlex
- W2400034325
- Cited by
- 72
- References
- 37
- Citations by year
- 2025: 4 · 2024: 5 · 2023: 4 · 2022: 7 · 2021: 3 · 2020: 5 · 2019: 10 · 2018: 22 · 2017: 9 · 2016: 3
- FWCI
- 12.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Conference on Decision and Control (CDC) (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
- Keywords
- distributed optimization, smoothness, linear convergence, strongly convex functions, gradient estimation, history information, convergence rate, nonsmooth optimization, communication complexity
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.