REVIEW 4 cited by
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithms that are provably robust against such failures, with a focus on achieving optimal statistical performance. A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively. We prove statistical error rates for three kinds of population loss functions: strongly convex, non-strongly convex, and smooth non-convex. In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses. To achieve better communication efficiency, we further propose a median-based distributed algorithm that is provably robust, and uses only one communication round. For strongly convex quadratic loss, we show that this algorithm achieves the same optimal error rate as the robust distributed gradient descent algorithms.
Forward citations
Cited by 4 Pith papers
-
Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach
FedSA uses sliding mode control on malicious local updates to drive a federated global model's test accuracy to a preset target while evading Byzantine-robust aggregators.
-
SMTFL: Secure Model Training to Untrusted Participants in Federated Learning
An FL scheme combining client grouping, gradient splitting, performance-based malicious detection, and threshold encryption aims to resist gradient inversion and poisoning attacks, claiming over 95% malicious-client l...
-
Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
Sentinel signs a TEE-attested record of each client's control-flow and variable usage and admits only updates whose attestation passes, reaching ASR 0 for its modeled attacks.
-
Optimizing Federated Learning Configurations for MRI Prostate Segmentation and Cancer Detection: A Simulation Study
Federated learning across simulated client datasets improved prostate MRI segmentation and cancer detection compared with local models, and configuration tuning improved detection performance.
Discussion (0). Continue with ORCID to comment.