aiqbench analysis
This paper introduces PCE-FedAvg, a federated learning algorithm designed to handle heterogeneous local constraints while enabling personalized models for each agent. By applying feasibility penalties locally without requiring agents to disclose their specific constraint sets, the method achieves distinct feasible models through collaborative objectives. Theoretical bounds on suboptimality and communication complexity are established and validated using standard image classification benchmarks.
A Locally Penalized Cross-Estimate Federated Method with Guarantees for Constrained Personalized Learning
arXiv:2603.19617v2 Announce Type: replace Abstract: Federated learning (FL) is a communication-efficient framework for solving distributed optimization problems. Standard FL methods aggregate local updates into a single global model that is shared by all agents, effectively imposing consensus. Under heterogeneous local constraints, however, a common feasible model may be overly restrictive or may not exist. Existing constrained FL methods largely retain this shared-model structure and therefore do not directly address personalization under heterogeneous agent-specific feasible sets. We study a constrained personalized FL problem that assigns a distinct feasible model to each agent while coupling the models through a collaborative objective. We propose Locally Penalized Cross-Estimate Federated Averaging (PCE-FedAvg), where each agent maintains a multi-block vector containing its own model and estimates of the other agents' models while applying the feasibility penalty only locally to its own block. The server aggregates corresponding blocks separately, thereby preserving personalization without requiring agents to explicitly disclose their local constraint sets. For any $\epsilon>0$, we establish finite-time upper and lower suboptimality bounds and agent-wise squared infeasibility bounds, yielding communication complexities of $\mathcal{O}(\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-1})$, respectively. Experiments on MNIST and CIFAR-10 support our theoretical results.
Abstract:Federated learning (FL) is a communication-efficient framework for solving distributed optimization problems. Standard FL methods aggregate local updates into a single global model that is shared by all agents, effectively imposing consensus. Under heterogeneous local constraints, however, a common feasible model may be overly restrictive or may not exist. Existing constrained FL methods largely retain this shared-model structure and therefore do not directly address personalization under heterogeneous agent-specific feasible sets. We study a constrained personalized FL problem that assigns a distinct feasible model to each agent while coupling the models through a collaborative objective. We propose Locally Penalized Cross-Estimate Federated Averaging (PCE-FedAvg), where each agent maintains a multi-block vector containing its own model and estimates of the other agents' models while applying the feasibility penalty only locally to its own block. The server aggregates corresponding blocks separately, thereby preserving personalization without requiring agents to explicitly disclose their local constraint sets. For any $\epsilon>0$, we establish finite-time upper and lower suboptimality bounds and agent-wise squared infeasibility bounds, yielding communication complexities of $\mathcal{O}(\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-1})$, respectively. Experiments on MNIST and CIFAR-10 support our theoretical results.
Machine Learning (cs.LG); Optimization and Control (math.OC)
arXiv:2603.19617 [cs.LG]
(or arXiv:2603.19617v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2603.19617 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 279 words
Related coverage
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026
[AINews] Opus 5.5 is good at explainer videos
Latent Space · Sep 29, 2026
FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning
arXiv · Sep 17, 2026