Byzantine-robust distributed support vector machine

The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine (known...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Science China. Mathematics Ročník 68; číslo 3; s. 707 - 728
Hlavní autoři: Wang, Xiaozhou, Liu, Weidong, Mao, Xiaojun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Beijing Science China Press 01.03.2025
Springer Nature B.V
Témata:
Algorithms
Applications of Mathematics
Data analysis
Estimators
Information technology
Machine learning
Mathematics
Mathematics and Statistics
Robustness
Support vector machines
distributed learning
62H30
68W15
Byzantine robustness
support vector machine
convergence
ISSN:1674-7283, 1869-1862
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine (known as Byzantine failures), which can invalidate the distributed algorithms based on the assumption of faultless systems. This paper studies Byzantine-robust distributed algorithms for support vector machines (SVMs) in the context of binary classification. Despite a vast literature on Byzantine problems, much less is known about the theoretical properties of Byzantine-robust SVMs due to their unique challenges. In this paper, we propose two distributed gradient descent algorithms for SVMs. The median and trimmed mean operations in aggregation can effectively defend against Byzantine failures. Theoretically, we show the convergence of the proposed estimators and provide the statistical error rates. After a certain number of iterations, our estimators achieve near-optimal rates. Simulation studies and real data analysis are conducted to demonstrate the performance of the proposed Byzantine-robust distributed algorithms.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1674-7283
1869-1862
DOI:10.1007/s11425-023-2217-2