On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression
Abstract
Federated learning (FL) is intrinsically heterogeneous: honest clients may have different data-generating models. On top of that, adversarial clients can make heterogeneity even more pronounced by sharing arbitrary updates. Existing analyses typically control the interaction between statistical heterogeneity and adversarial behavior through gradient-dissimilarity conditions. However, the underlying bound is imposed a priori and may yield conservative guarantees even for least-squares regression. We instead derive the gradient heterogeneity from the statistical model of linear and nonlinear regression with fresh data samples at every round. Our bounds separate heterogeneity among the honest clients' ground-truth model parameters, finite-sample label noise, and initialization. We then demonstrate that, for any (f,κ)-robust aggregator with coefficient κ= O(f/n), where f is the number of adversarial clients and n the total number of clients (with f/n < 1/2), convergence holds after an explicit sample burn-in.
Related
- Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics
- Large Stepsizes Federated Learning on Logistic Regression with Linearly Separable Data: The Case of Heterogeneous Devices
- Hybrid Federated Learning for Multimodal Fusion under Missing Modalities and Site Heterogeneity
- Federated Time-to-Event Data Analysis Using Piecewise Exponential Regression in DataSHIELD.
- Federated Nonparametric Regression with Heterogeneous Clients
BibTeX
@misc{toso2026gradient,
title = {{On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression}},
author = {Leonardo F. Toso and James Anderson and Nirupam Gupta and Rafael Pinot},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25705},
eprint = {2609.25705},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25705},
}
RIS
TY - UNPB
TI - On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression
AU - Leonardo F. Toso
AU - James Anderson
AU - Nirupam Gupta
AU - Rafael Pinot
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.25705
UR - https://arxiv.org/abs/2609.25705
AB - Federated learning (FL) is intrinsically heterogeneous: honest clients may have different data-generating models. On top of that, adversarial clients can make heterogeneity even more pronounced by sharing arbitrary updates. Existing analyses typically control the interaction between statistical heterogeneity and adversarial behavior through gradient-dissimilarity conditions. However, the underlying bound is imposed a priori and may yield conservative guarantees even for least-squares regression. We instead derive the gradient heterogeneity from the statistical model of linear and nonlinear regression with fresh data samples at every round. Our bounds separate heterogeneity among the honest clients' ground-truth model parameters, finite-sample label noise, and initialization. We then demonstrate that, for any (f,κ)-robust aggregator with coefficient κ= O(f/n), where f is the number of adversarial clients and n the total number of clients (with f/n < 1/2), convergence holds after an explicit sample burn-in.
ER -