Communication-Efficient Distributed Linear Discriminant Analysis for Binary Classification

Li, Mengyu; Zhao, Junwei

doi:10.5705/ss.202020.0374

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The situation of Fisher faces [ 3 ] is similar to that of eigenfaces, but they differ in that Fisher faces also include a concept known as LDA which stands for linear discriminant analysis [ 4 ]. This addition makes it possible to extract characteristics according to the classes in opposition in the consideration of images taken as samples as a during the process of extraction of eigenvalues.…”

Section: Related Workmentioning

confidence: 99%

RoFace: A robust face representation approach for accurate classification

Fute

Deffo

Tonyé

2023

Heliyon

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

RoFace: A robust face representation approach for accurate classification

Fute

Deffo

Tonyé

2023

Heliyon

View full text Add to dashboard Cite

“…The divide and conquer technique is a popular method in distributed frameworks, where one constructs a statistic or an estimator using data in each machine, and then transmits them to the hub to get a pooled one. The divide and conquer technique has been applied successfully in many problems, including regression and classification, hypothesis testing, confidence intervals, principal eigenspaces analysis, linear discriminant analysis, and many others (Zhang et al, 2013;Hsieh et al, 2014;Zhang et al, 2015;Lin et al, 2017;Szabó and Van Zanten, 2019;Battey et al, 2018;Guo et al, 2019;Chen and Peng, 2018;Jordan et al, 2019;Fan et al, 2019;Tian and Gu, 2017;Li and Zhao, 2020;Dobriban and Sheng, 2021, etc. ).…”

Section: Introductionmentioning

confidence: 99%

Hypothesis Testing of One-Sample Mean Vector in Distributed Frameworks

Du,

Zhao

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Distributed frameworks are widely used to handle massive data, where sample size n is very large, and data are often stored in k different machines. For a random vector X ∈ R p with expectation µ, testing the mean vector H 0 : µ = µ 0 vs H 1 : µ = µ 0 for a given vector µ 0 is a basic problem in statistics. The centralized test statistics require heavy communication costs, which can be a burden when p or k is large. To reduce the communication cost, distributed test statistics are proposed in this paper for this problem based on the divide and conquer technique, a commonly used approach for distributed statistical inference. Specifically, we extend two commonly used centralized test statistics to the distributed ones, that apply to low and high dimensional cases, respectively. Comparing the power of centralized test statistics and the distributed ones, it is observed that there is a fundamental tradeoff between communication costs and powers of the tests. This is quite different from the application of the divide and conquer technique in many other problems such as estimation, where the associated distributed statistics can be as good as the centralized ones. Numerical results confirm the theoretical findings.

show abstract