ByMI: Byzantine Machine Identification with False Discovery Rate Control

Chengde Qian, Mengyuan Wang, Haojie Ren, Changliang Zou
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41357-41382, 2024.

Abstract

Various robust estimation methods or algorithms have been proposed to hedge against Byzantine failures in distributed learning. However, there is a lack of systematic approaches to provide theoretical guarantees of significance in detecting those Byzantine machines. In this paper, we develop a general detection procedure, ByMI, via error rate control to address this issue, which is applicable to many robust learning problems. The key idea is to apply the sample-splitting strategy on each worker machine to construct a score statistic integrated with a general robust estimation and then to utilize the symmetry property of those scores to derive a data-driven threshold. The proposed method is dimension insensitive and p-value free with the help of the symmetry property and can achieve false discovery rate control under mild conditions. Numerical experiments on both synthetic and real data validate the theoretical results and demonstrate the effectiveness of our proposed method on Byzantine machine identification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-qian24b, title = {{B}y{MI}: {B}yzantine Machine Identification with False Discovery Rate Control}, author = {Qian, Chengde and Wang, Mengyuan and Ren, Haojie and Zou, Changliang}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {41357--41382}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/qian24b/qian24b.pdf}, url = {https://proceedings.mlr.press/v235/qian24b.html}, abstract = {Various robust estimation methods or algorithms have been proposed to hedge against Byzantine failures in distributed learning. However, there is a lack of systematic approaches to provide theoretical guarantees of significance in detecting those Byzantine machines. In this paper, we develop a general detection procedure, ByMI, via error rate control to address this issue, which is applicable to many robust learning problems. The key idea is to apply the sample-splitting strategy on each worker machine to construct a score statistic integrated with a general robust estimation and then to utilize the symmetry property of those scores to derive a data-driven threshold. The proposed method is dimension insensitive and p-value free with the help of the symmetry property and can achieve false discovery rate control under mild conditions. Numerical experiments on both synthetic and real data validate the theoretical results and demonstrate the effectiveness of our proposed method on Byzantine machine identification.} }
Endnote
%0 Conference Paper %T ByMI: Byzantine Machine Identification with False Discovery Rate Control %A Chengde Qian %A Mengyuan Wang %A Haojie Ren %A Changliang Zou %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-qian24b %I PMLR %P 41357--41382 %U https://proceedings.mlr.press/v235/qian24b.html %V 235 %X Various robust estimation methods or algorithms have been proposed to hedge against Byzantine failures in distributed learning. However, there is a lack of systematic approaches to provide theoretical guarantees of significance in detecting those Byzantine machines. In this paper, we develop a general detection procedure, ByMI, via error rate control to address this issue, which is applicable to many robust learning problems. The key idea is to apply the sample-splitting strategy on each worker machine to construct a score statistic integrated with a general robust estimation and then to utilize the symmetry property of those scores to derive a data-driven threshold. The proposed method is dimension insensitive and p-value free with the help of the symmetry property and can achieve false discovery rate control under mild conditions. Numerical experiments on both synthetic and real data validate the theoretical results and demonstrate the effectiveness of our proposed method on Byzantine machine identification.
APA
Qian, C., Wang, M., Ren, H. & Zou, C.. (2024). ByMI: Byzantine Machine Identification with False Discovery Rate Control. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:41357-41382 Available from https://proceedings.mlr.press/v235/qian24b.html.

Related Material