arXiv Open Access 2022

Top-k data selection via distributed sample quantile inference

Xu Zhang Marcos Vasconcelos
Lihat Sumber

Abstrak

We consider the problem of determining the top-$k$ largest measurements from a dataset distributed among a network of $n$ agents with noisy communication links. We show that this scenario can be cast as a distributed convex optimization problem called sample quantile inference, which we solve using a two-time-scale stochastic approximation algorithm. Herein, we prove the algorithm's convergence in the almost sure sense to an optimal solution. Moreover, our algorithm handles noise and empirically converges to the correct answer within a small number of iterations.

Topik & Kata Kunci

Penulis (2)

X

Xu Zhang

M

Marcos Vasconcelos

Format Sitasi

Zhang, X., Vasconcelos, M. (2022). Top-k data selection via distributed sample quantile inference. https://arxiv.org/abs/2212.00230

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓