Top-k data selection via distributed sample quantile inference

Xu Zhang, Marcos M. Vasconcelos
Proceedings of The 5th Annual Learning for Dynamics and Control Conference, PMLR 211:813-824, 2023.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v211-zhang23d, title = {Top-k data selection via distributed sample quantile inference}, author = {Zhang, Xu and Vasconcelos, Marcos M.}, booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference}, pages = {813--824}, year = {2023}, editor = {Matni, Nikolai and Morari, Manfred and Pappas, George J.}, volume = {211}, series = {Proceedings of Machine Learning Research}, month = {15--16 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v211/zhang23d/zhang23d.pdf}, url = {https://proceedings.mlr.press/v211/zhang23d.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Top-k data selection via distributed sample quantile inference %A Xu Zhang %A Marcos M. Vasconcelos %B Proceedings of The 5th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2023 %E Nikolai Matni %E Manfred Morari %E George J. Pappas %F pmlr-v211-zhang23d %I PMLR %P 813--824 %U https://proceedings.mlr.press/v211/zhang23d.html %V 211 %X 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.
APA
Zhang, X. & Vasconcelos, M.M.. (2023). Top-k data selection via distributed sample quantile inference. Proceedings of The 5th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 211:813-824 Available from https://proceedings.mlr.press/v211/zhang23d.html.

Related Material