The DOI matches its Crossref record; 51 of the 53 references it cites were found in a registry or an index.
Decentralized Stochastic Optimization and Machine Learning: A Unified Variance-Reduction Framework for Robust Performance and Fast Convergence
Abstract
Decentralized methods to solve finite-sum minimization problems are important in many signal processing and machine learning tasks where the data samples are distributed across a network of nodes, and raw data sharing is not permitted due to privacy and/or resource constraints. In this article, we review decentralized stochastic first-order methods and provide a unified algorithmic framework that combines variance reduction with gradient tracking to achieve robust performance and fast convergence. We provide explicit theoretical guarantees of the corresponding methods when the objective functions are smooth and strongly convex and show their applicability to nonconvex problems via numerical experiments. Throughout the article, we provide intuitive illustrations of the main technical ideas by casting appropriate tradeoffs and comparisons among the methods of interest and by highlighting applications to decentralized training of machine learning models.
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
“Specifically, the variance reduction with the gradient tracking method was investigated in [146] to achieve a fast convergence rate.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [146]
Citations
Cites
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 3×
“…where the objective functions are smooth and strongly convex [2]; text classification with support vector machines, where the objectives are convex but not necessarily smooth [1]; and perception tasks with deep neural networks, where the cost functions are nonconvex, in general [1], [2].”
BackgroundMethodInfluentialCommunication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 1×
“Various programming models and several variants of master–worker configurations that are tailored for specific computing needs and environments have been proposed, such as MapReduce, AllReduce, and federated learning [50].”
BackgroundConsensus 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 3×
“…, ; i 6 and 2) optimality—the agreement should be on the minimizer of the global objective F , i.e., . cons i i = ) Average-consensus algorithms [10] are information fusion protocols that enable each node to appropriately combine the vectors received from its neighbors and agree on the average…”
BackgroundMethodResultInfluentialHorn, R. A., & Johnson, C. R. (2012) · doi:10.1017/cbo9781139020411 · Cited by 4,642
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 1×
“A well-known solution to this problem is DGD [13], [14], described as follows.”
MethodOptimization Methods for Large-Scale Machine Learning
Bottou, L., Curtis, F. E., & Nocedal, J. (2018) · SIAM Review · doi:10.1137/16m1080173 · Cited by 3,128
Accelerating Stochastic Gradient Descent using Predictive Variance Reduction
Johnson, R., & Zhang, T. (2013) · Cited by 1,889
Gossip-based computation of aggregate information
Kempe, D., Dobra, A., & Gehrke, J. (2004) · 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings. · doi:10.1109/sfcs.2003.1238221 · Cited by 1,480 · cited 1×
“A well-studied solution to this issue is based on the push-sum (type) algorithms [39] that enable consensus with non-DS weights through the help of eigenvector estimation.”
MethodPattern Recognition and Machine Learning
Maindonald, J. (2007) · Journal of Statistical Software · doi:10.18637/jss.v017.b05 · Cited by 1,349
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
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 · cited 1×
“Combining push-sum, respectively, with DSGD [14], [15] and GT-DGD [20]–[22] leads to SGP [40] and ADD–OPT [41], which require CS weights.”
MethodLectures on Convex Optimization
Nesterov, Y. (2018) · Springer Optimization and Its Applications · doi:10.1007/978-3-319-91578-4 · Cited by 1,010
Minimizing finite sums with the stochastic average gradient
Schmidt, M., Le Roux, N., & Bach, F. (2017) · Mathematical Programming · doi:10.1007/s10107-016-1030-6 · Cited by 922 · cited 5×
“Different constructions of the afore-mentioned gradient estimator lead to different variance reduction methods [6]–[9].”
BackgroundMethodInfluentialSAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
Defazio, A., Bach, F., & Lacoste-Julien, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.0202 · Cited by 834 · cited 5×
“Although SAGA and SVRG, in theory, achieve convergence rates of the same order, SVRG, in practice, requires two to three times more component gradient evaluations to reach the same accuracy as SAGA, however, without storing all the component gradients [7].”
BackgroundMethodInfluentialDistributed Stochastic Subgradient Projection Algorithms for Convex Optimization
Sundhar Ram, S., Nedić, A., & Veeravalli, V. V. (2010) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-010-9737-7 · Cited by 814 · cited 2×
“To make DGD efficient for large-scale decentralized empirical risk minimization, where each m i is very large, [14] and [15] derive a stochastic variant, known as DSGD , by substituting each local batch gradient with a randomly sampled component gradient.”
MethodDiffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks
Chen, J., & Sayed, A. H. (2012) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2012.2198470 · Cited by 680 · cited 3×
“To make DGD efficient for large-scale decentralized empirical risk minimization, where each m i is very large, [14] and [15] derive a stochastic variant, known as DSGD , by substituting each local batch gradient with a randomly sampled component gradient.”
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
Network 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
Discrete-time dynamic average consensus
Zhu, M., & Martínez, S. (2010) · Automatica · doi:10.1016/j.automatica.2009.10.021 · Cited by 488
NEXT: In-Network Nonconvex Optimization
Lorenzo, P. D., & Scutari, G. (2016) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2016.2524588 · Cited by 473 · cited 1×
“Require: Choose s ki uniformly at random in { , , } m 1 i f Compute the local stochastic gradient ( ) ki i 5: end for thus combine DGD (9) and DAC (15) to obtain GT-DGD [19]– [23] as follows: where , . i 6 ( ) i 0 i 16a) asymptotically becomes the centralized batch gradient descent.”
BackgroundStochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm
Needell, D., Srebro, N., & Ward, R. (2016) · Mathematical Programming · doi:10.1007/s10107-015-0864-7 · Cited by 432 · cited 1×
“This assumption, however, can be relaxed; for example, see [1], [4], and [5].)”
BackgroundLian, X., Zhang, C., Zhang, H., Hsieh, C., Zhang, W., & Liu, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.09056 · Cited by 395 · cited 1×
“The problems described in this article have attracted significant research interest because of their direct applicability to large-scale training problems in machine learning [40], [49].”
BackgroundXu, J., Zhu, S., Soh, Y. C., & Xie, L. (2015) · 2015 54th IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402509 · Cited by 332 · cited 1×
“Combining push-sum, respectively, with DSGD [14], [15] and GT-DGD [20]–[22] leads to SGP [40] and ADD–OPT [41], which require CS weights.”
MethodSARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive GradientPreprint
Nguyen, L. M., Liu, J., Scheinberg, K., & Takáč, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00102 · Cited by 325 · cited 3×
“Different constructions of the afore-mentioned gradient estimator lead to different variance reduction methods [6]–[9].”
BackgroundMethodStochastic Gradient Push for Distributed Deep LearningPreprint
Assran, M., Loizou, N., Ballas, N., & Rabbat, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.10792 · Cited by 253 · cited 2×
“The problems described in this article have attracted significant research interest because of their direct applicability to large-scale training problems in machine learning [40], [49].”
BackgroundMethodA 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 · cited 4×
“Require: Choose s ki uniformly at random in { , , } m 1 i f Compute the local stochastic gradient ( ) ki i 5: end for thus combine DGD (9) and DAC (15) to obtain GT-DGD [19]– [23] as follows: where , . i 6 ( ) i 0 i 16a) asymptotically becomes the centralized batch gradient descent.”
BackgroundInfluentialSelf-citationExact Diffusion for Distributed Optimization and Learning—Part I: Algorithm Development
Yuan, K., Ying, B., Zhao, X., & Sayed, A. H. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2875898 · Cited by 200 · cited 2×
“Of relevance here are EX-TRA [27] and exact diffusion [28], both of which eliminate the bias caused by b and are built different principle than gradient tracking.”
BackgroundCommunication-efficient algorithms for decentralized and stochastic optimization
Lan, G., Lee, S., & Zhou, Y. (2020) · Mathematical Programming · doi:10.1007/s10107-018-1355-4 · Cited by 187 · cited 1×
“Different communication-efficient schemes [45], [36], communication/computation tradeoffs [11], asynchronous implementations [46], and quantization techniques [47], [48] have been studied with existing decentralized methods to efficiently manage the resources at each node.”
BackgroundADD-OPT: Accelerated Distributed Directed Optimization
Xi, C., Xin, R., & Khan, U. A. (2018) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2017.2737582 · Cited by 181 · cited 1×
“Combining push-sum, respectively, with DSGD [14], [15] and GT-DGD [20]–[22] leads to SGP [40] and ADD–OPT [41], which require CS weights.”
MethodSelf-citationDecentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
Koloskova, A., Stich, S. U., & Jaggi, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00340 · Cited by 163 · cited 1×
“Different communication-efficient schemes [45], [36], communication/computation tradeoffs [11], asynchronous implementations [46], and quantization techniques [47], [48] have been studied with existing decentralized methods to efficiently manage the resources at each node.”
BackgroundSGD: General Analysis and Improved RatesPreprint
Gower, R. M., Loizou, N., Qian, X., Sailanbayev, A., Shulgin, E., & Richtárik, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09401 · Cited by 157 · cited 1×
“This assumption, however, can be relaxed; for example, see [1], [4], and [5].)”
BackgroundAn Exact Quantized Decentralized Gradient Descent Algorithm
Reisizadeh, A., Mokhtari, A., Hassani, H., & Pedarsani, R. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2932876 · Cited by 142 · cited 1×
“Different communication-efficient schemes [45], [36], communication/computation tradeoffs [11], asynchronous implementations [46], and quantization techniques [47], [48] have been studied with existing decentralized methods to efficiently manage the resources at each node.”
BackgroundDSA: Decentralized Double Stochastic Averaging Gradient AlgorithmPreprint
Mokhtari, A., & Ribeiro, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04216 · Cited by 141 · cited 1×
“Existing decentralized variance reduction methods include DSA [30], which combines EXTRA [27] with SAGA [7]; diffusion–amortized variance-reduced gradient (AVRG), which combines exact diffusion [28] and AVRG [31]; DSBA [32], which adds proximal mapping [33] to each iteration of DSA; ADFS [34],…”
MethodLin, Q., Lu, Z., & Xiao, L. (2015) · SIAM Journal on Optimization · doi:10.1137/141000270 · Cited by 135 · cited 1×
“…which adds proximal mapping [33] to each iteration of DSA; ADFS [34], which applies an accelerated randomized proximal coordinate gradient method [35] to the dual formulation of Problem P3; and network–SVRG/SARAH [36], which implements variance reduction in the decentralized DANE framework based…”
MethodVariance-Reduced Decentralized Stochastic Optimization With Accelerated Convergence
Xin, R., Khan, U. A., & Kar, S. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3031071 · Cited by 128 · cited 3×
“More precisely, assuming each f S , , i j L ! n and by choosing { ( /( )), (( / ) min M m M 1 O O a n = / ( }, ( ) )) L 1 2 m l where { }, min m m i i = { }, max M m i i = we have [29]”
BackgroundMethodInfluentialSelf-citationFROST—Fast row-stochastic optimization with uncoordinated step-sizes
Xin, R., Xi, C., & Khan, U. A. (2019) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-018-0596-y · Cited by 122 · cited 1×
“A similar idea is used in FROST [42] to implement decentralized optimization with RS weights.”
MethodSelf-citationDistributed stochastic optimization with gradient tracking over strongly-connected networks
Xin, R., Sahu, A. K., Khan, U. A., & Kar, S. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029217 · Cited by 122 · cited 1×
“The AB framework naturally leads to stochastic optimization with gradient tracking across directed graphs; see SAB [44] that extends GT-DSGD to directed graphs and further opens the possibility to extend GT-SAGA and GT-SVRG to their directed counterparts.”
BackgroundSelf-citationA Push-Pull Gradient Method for Distributed Optimization in Networks
Pu, S., Shi, W., Xu, J., & Nedić, A. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619047 · Cited by 104
AsySPA: An Exact Asynchronous Algorithm for Convex Optimization Over Digraphs
Zhang, J., & You, K. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2930234 · Cited by 94 · cited 1×
“Different communication-efficient schemes [45], [36], communication/computation tradeoffs [11], asynchronous implementations [46], and quantization techniques [47], [48] have been studied with existing decentralized methods to efficiently manage the resources at each node.”
BackgroundA Simple Practical Accelerated Method for Finite SumsPreprint
Defazio, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02442 · Cited by 78 · cited 1×
“…diffusion–amortized variance-reduced gradient (AVRG), which combines exact diffusion [28] and AVRG [31]; DSBA [32], which adds proximal mapping [33] to each iteration of DSA; ADFS [34], which applies an accelerated randomized proximal coordinate gradient method [35] to the dual formulation of…”
MethodVariance-Reduced Stochastic Learning by Networked Agents Under Random Reshuffling
Yuan, K., Ying, B., Liu, J., & Sayed, A. H. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2872003 · Cited by 78 · cited 1×
“The nodes cooperate to solve the following problem: the regularization parameter is / , N 1 m = and the features are normalized to unit vectors [6], [38].”
BackgroundA Linearly Convergent Proximal Gradient Algorithm for Decentralized OptimizationPreprint
Alghunaim, S. A., Yuan, K., & Sayed, A. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07996 · Cited by 76 · cited 1×
“It has been shown in [21]–[23] and [25] that GT-DGD converges linearly to the minimizer i of F under a constant step-size when each , f S , , i j L ! n unlike DGD that converges sublinearly to i with decaying step-sizes.”
BackgroundConvergence Rates for Distributed Stochastic Optimization Over Random Networks
Jakovetić, D., Bajović, D., Sahu, A. K., & Kar, S. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619228 · Cited by 71 · cited 1×
“…assumption can be relaxed, as noted previously, see [16]), i.e., ( ) ( ) , , , i k ki ki 6 i i we have [16]: DSGD achieves an exact convergence [17], [18] Remark 3: SGD versus DSGD Comparing (3) with (12), when a constant step-size a is used, the steady-state error in both SGD and DSGD decays…”
BackgroundSelf-citationA Distributed Stochastic Gradient Tracking Method
Pu, S., & Nedić, A. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8618708 · Cited by 70
Shen, Z., Mokhtari, A., Zhou, T., Zhao, P., & Qian, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09969 · Cited by 54 · cited 1×
“…combines EXTRA [27] with SAGA [7]; diffusion–amortized variance-reduced gradient (AVRG), which combines exact diffusion [28] and AVRG [31]; DSBA [32], which adds proximal mapping [33] to each iteration of DSA; ADFS [34], which applies an accelerated randomized proximal coordinate gradient…”
MethodVariance-Reduced Stochastic Learning Under Random Reshuffling
Ying, B., Yuan, K., & Sayed, A. H. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2968280 · Cited by 38 · cited 2×
“Existing decentralized variance reduction methods include DSA [30], which combines EXTRA [27] with SAGA [7]; diffusion–amortized variance-reduced gradient (AVRG), which combines exact diffusion [28] and AVRG [31]; DSBA [32], which adds proximal mapping [33] to each iteration of DSA; ADFS [34], which applies an acceler…”
MethodAsynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite SumsPreprint
Hendrikx, H., Bach, F., & Massoulié, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09865 · Cited by 23 · cited 1×
“…gradient (AVRG), which combines exact diffusion [28] and AVRG [31]; DSBA [32], which adds proximal mapping [33] to each iteration of DSA; ADFS [34], which applies an accelerated randomized proximal coordinate gradient method [35] to the dual formulation of Problem P3; and network–SVRG/SARAH…”
MethodA Non-Asymptotic Analysis of Network Independence for Distributed Stochastic Gradient DescentPreprint
Olshevsky, A., Paschalidis, I. C., & Pu, S. (2019) · arXiv (Cornell University) · Cited by 13
Decentralized double stochastic averaging gradient
Mokhtari, A., & Ribeiro, A. (2015) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2015.7421158 · Cited by 12
On the Performance of Exact Diffusion over Adaptive Networks
Yuan, K., Alghunaim, S. A., Ying, B., & Sayed, A. H. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029537 · Cited by 10 · cited 2×
“Assuming that each f S , , i j L ! n and every local stochastic gradient has bounded variance (this assumption can be relaxed, as noted previously, see [16]), i.”
BackgroundCommunication-Efficient Distributed Optimization in Networks with Gradient Tracking.
Li, B., Cen, S., Chen, Y., & Chi, Y. (2019) · Cited by 7
Research works printed but not linked: 1
- lecun, 1998, The MNIST Database of Handwritten Digits
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“Specifically, the variance reduction with the gradient tracking method was investigated in [146] to achieve a fast convergence rate.”
MethodTwelve Scientific Challenges for 6G: Rethinking the Foundations of Communications Theory
Chafii, M., Bariah, L., Muhaidat, S., & Debbah, M. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3243918 · Cited by 289
“With the aim to enable self-optimizing large-scale networks, decentralized stochastic optimization is proposed as an efficient method to realize network-wide optimization, with leveraging a large number of resources-constrained devices which communicate with each other in a decentralized ad-hoc manner [126].”
MethodFederated Learning Over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis
Xing, H., Simeone, O., & Bi, S. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118400 · Cited by 160
“There are important scenarios in which a base station-centric architecture is either unavailable or undesirable due to coverage, privacy, implementation efficiency, or fault-tolerance considerations [14], [15].”
BackgroundA General Framework for Decentralized Optimization With First-Order Methods
Xin, R., Pu, S., Nedić, A., & Khan, U. A. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3024266 · Cited by 148
“Remark 19 (Other instances of the GT-VR framework): The discussion in this section enables a suite of methods that combine various gradient tracking and variance reduction techniques leading to different performance and implementation trade-offs towards different problem classes [21], [69].”
BackgroundMethodInfluentialSelf-citationAn Improved Convergence Analysis for Decentralized Online Stochastic Non-Convex Optimization
Xin, R., Khan, U. A., & Kar, S. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3062553 · Cited by 147
“P For further intuition and explanation, see [2], [10], for example.”
BackgroundSelf-citation
Metadata
- Authors
- Xin, R., Kar, S., & Khan, U. A.
- Affiliations
- Carnegie Mellon University (US)
- Tufts University (US)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2020-05
- Volume
- 37
- Issue
- 3
- Pages
- 102-113
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W3023944502
- Cited by
- 114
- References
- 53
- Citations by year
- 2026: 5 · 2025: 15 · 2024: 13 · 2023: 16 · 2022: 28 · 2021: 22 · 2020: 13
- FWCI
- 7.76
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- Funders
- National Science Foundation (CCF-1350264; CCF-1513936; CMMI-1903972; CBET-1935555)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- distributed optimization, stochastic optimization, variance reduction, gradient tracking, finite-sum minimization, decentralized machine learning, decentralized learning, non-convex optimization, strong convexity, convergence guarantees, privacy-preserving machine learning
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.