Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent

Chen, Yudong, Su, Lili, Xu, Jiaming · 2017 · Proceedings of the ACM on Measurement and Analysis of Computing Systems

Abstract

We consider the distributed statistical learning problem over decentralized systems that are prone to adversarial attacks. This setup arises in many practical applications, including Google's Federated Learning. Formally, we focus on a decentralized system that consists of a parameter server and m working machines; each working machine keeps N/m data samples, where N is the total number of samples. In each iteration, up to q of the m working machines suffer Byzantine faults -- a faulty machine in the given iteration behaves arbitrarily badly against the system and has complete knowledge of the system. Additionally, the sets of faulty machines may be different across iterations. Our goal is to design robust algorithms such that the system can learn the underlying true parameter, which is of dimension d, despite the interruption of the Byzantine attacks. In this paper, based on the geometric median of means of the gradients, we propose a simple variant of the classical gradient descent method. We show that our method can tolerate q Byzantine failures up to 2(1+ε)q ≤ for an arbitrarily small but fixed constant ε > 0. The parameter estimate converges in O(log N) rounds with an estimation error on the order of max{√dq/N, √d/N, which is larger than the minimax-optimal error rate √d/N in the centralized and failure-free setting by at most a factor of √q. The total computational complexity of our algorithm is of O((Nd/m) log N) at each working machine and O(md + kd log3 N) at the cen…

Overview

Integrity signals

Registry

Crossref · 10.1145/3154503

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Show all 15 references

Research works printed but not linked: 15

  1. Peva Blanchard , El Mahdi El Mhamdi , Rachid Guerraoui, and Julien Stainer. 2017 . Byzantine-Tolerant Machine Learning . arXiv preprint arXiv:1703.02757 (2017). Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer. 2017. Byzantine-Tolerant Machine Learning. arXiv preprint arXiv:1703.02757 (2017). · arXiv
  2. Stephen Boyd and Lieven Vandenberghe . 2004. Convex optimization . Cambridge university press . Stephen Boyd and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press.
  3. John Duchi Martin J Wainwright and Michael I Jordan. 2013. Local privacy and minimax bounds: Sharp rates for probability estimation. Advances in Neural Information Processing Systems. 1529--1537. John Duchi Martin J Wainwright and Michael I Jordan. 2013. Local privacy and minimax bounds: Sharp rates for probability estimation. Advances in Neural Information Processing Systems. 1529--1537.
  4. Jiashi Feng , Huan Xu , and Shie Mannor . 2014. Distributed Robust Learning. arXiv preprint arXiv:1409.5937 ( 2014 ). Jiashi Feng, Huan Xu, and Shie Mannor. 2014. Distributed Robust Learning. arXiv preprint arXiv:1409.5937 (2014). · arXiv
  5. Michael I Jordan , Jason D Lee , and Yun Yang . 2016. Communication-Efficient Distributed Statistical Inference. arXiv preprint arXiv:1605.07689 ( 2016 ). Michael I Jordan, Jason D Lee, and Yun Yang. 2016. Communication-Efficient Distributed Statistical Inference. arXiv preprint arXiv:1605.07689 (2016). · arXiv
  6. JHB Kemperman . 1987. The median of a finite measure on a Banach space. Statistical data analysis based on the L1-norm and related methods (Neuchâtel , 1987 ) (1987), 217--230. JHB Kemperman. 1987. The median of a finite measure on a Banach space. Statistical data analysis based on the L1-norm and related methods (Neuchâtel, 1987) (1987), 217--230.
  7. Jakub Konevcnỳ , Brendan McMahan , and Daniel Ramage . 2015. Federated optimization: Distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 ( 2015 ). Jakub Konevcnỳ, Brendan McMahan, and Daniel Ramage. 2015. Federated optimization: Distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 (2015). · arXiv
  8. Hendrik P Lopuhaa and Peter J Rousseeuw . 1991. Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. The Annals of Statistics ( 1991 ), 229--248. Hendrik P Lopuhaa and Peter J Rousseeuw. 1991. Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. The Annals of Statistics (1991), 229--248.
  9. Nancy A. Lynch . 1996. Distributed Algorithms . Morgan Kaufmann Publishers Inc ., San Francisco, CA, USA. \showISBNx9780080504704 Nancy A. Lynch. 1996. Distributed Algorithms. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. \showISBNx9780080504704
  10. Song Mei , Yu Bai , and Andrea Montanari . 2016. The landscape of empirical risk for non-convex losses. arXiv preprint arXiv:1607.06534 ( 2016 ). Song Mei, Yu Bai, and Andrea Montanari. 2016. The landscape of empirical risk for non-convex losses. arXiv preprint arXiv:1607.06534 (2016). · arXiv
  11. Philipp Moritz , Robert Nishihara , Ion Stoica , and Michael I Jordan . 2015 . Sparknet: Training deep networks in spark. arXiv preprint arXiv:1511.06051 (2015). Philipp Moritz, Robert Nishihara, Ion Stoica, and Michael I Jordan. 2015. Sparknet: Training deep networks in spark. arXiv preprint arXiv:1511.06051 (2015). · arXiv
  12. Charles P. Pfleeger and Shari Lawrence Pfleeger . 2002 . Security in Computing (3rd ed.). Prentice Hall Professional Technical Reference . Charles P. Pfleeger and Shari Lawrence Pfleeger. 2002. Security in Computing (3rd ed.). Prentice Hall Professional Technical Reference.
  13. Foster J Provost and Daniel N Hennessy . 1996 . Scaling up: Distributed machine learning with cooperation . AAAI/IAAI , Vol. 1 . Citeseer, 74--79. Foster J Provost and Daniel N Hennessy. 1996. Scaling up: Distributed machine learning with cooperation. AAAI/IAAI, Vol. 1. Citeseer, 74--79.
  14. R. Vershynin . 2010. Introduction to the non-asymptotic analysis of random matrices. Arxiv preprint arxiv:1011.3027 ( 2010 ). R. Vershynin. 2010. Introduction to the non-asymptotic analysis of random matrices. Arxiv preprint arxiv:1011.3027 (2010). · arXiv
  15. 10.5555/1833515.1833620 · doi:10.5555/1833515.1833620

Cited by

See all 390

Metadata

Authors
Chen, Y., Su, L., & Xu, J.
Affiliations
  • Cornell University (US)
  • University of Illinois Urbana-Champaign (US)
  • Purdue University West Lafayette (US)
Venue
Proceedings of the ACM on Measurement and Analysis of Computing Systems
Published
2017-12-19
Volume
1
Issue
2
Pages
1-25
ISSN
2476-1249 (ISSN-L)
OpenAlex
W4252654521
Cited by
390
References
15
Citations by year
2026: 36 · 2025: 85 · 2024: 68 · 2023: 61 · 2022: 47 · 2021: 44 · 2020: 28 · 2019: 14 · 2018: 7
FWCI
8.00
Type
journal article
Language
en
Open access
closed
Locations
Proceedings of the ACM on Measurement and Analysis of Computing Systems (publishedVersion)
Funders
NSF (CRII award 1657420; CCF-1704828; ECCS-1610543; CCF-0939370)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
  • Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
Keywords
Byzantine faults, federated learning, decentralized systems, parameter server, linear regression, 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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent. https://app.cochat.ai/papers/10.1145/3154503
The paper
Chen, Y., Su, L., & Xu, J. (2017). Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent. Proceedings of the ACM on Measurement and Analysis of Computing Systems. https://doi.org/10.1145/3154503

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.