Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911496475246592 |
|---|---|
| author | Qiu, Pu Ouyang, Chen Xiong, Yongyang You, Keyou Liu, Wanquan Shi, Yang |
| author_facet | Qiu, Pu Ouyang, Chen Xiong, Yongyang You, Keyou Liu, Wanquan Shi, Yang |
| contents | Federated Composite Optimization (FCO) has emerged as a promising framework for training models with structural constraints (e.g., sparsity) in distributed edge networks. However, simultaneously achieving communication efficiency and convergence robustness remains a significant challenge, particularly when dealing with non-smooth regularizers, statistical heterogeneity, and the restrictions of biased compression. To address these issues, we propose FedCEF (Federated Composite Error Feedback), a novel algorithm tailored for non-convex FCO. FedCEF introduces a decoupled proximal update scheme that separates the proximal operator from communication, enabling clients to handle non-smooth terms locally while transmitting compressed information. To mitigate the noise from aggressive quantization and the bias from non-IID data, FedCEF integrates a rigorous error feedback mechanism with control variates. Furthermore, we design a communication-efficient pre-proximal downlink strategy that allows clients to exactly reconstruct global control variables without explicit transmission. We theoretically establish that FedCEF achieves sublinear convergence to a bounded residual error under general non-convexity, which is controllable via the step size and batch size. Extensive experiments on real datasets validate FedCEF maintains competitive model accuracy even under extreme compression ratios (e.g., 1%), significantly reducing the total communication volume compared to uncompressed baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07654 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data Qiu, Pu Ouyang, Chen Xiong, Yongyang You, Keyou Liu, Wanquan Shi, Yang Optimization and Control Machine Learning Federated Composite Optimization (FCO) has emerged as a promising framework for training models with structural constraints (e.g., sparsity) in distributed edge networks. However, simultaneously achieving communication efficiency and convergence robustness remains a significant challenge, particularly when dealing with non-smooth regularizers, statistical heterogeneity, and the restrictions of biased compression. To address these issues, we propose FedCEF (Federated Composite Error Feedback), a novel algorithm tailored for non-convex FCO. FedCEF introduces a decoupled proximal update scheme that separates the proximal operator from communication, enabling clients to handle non-smooth terms locally while transmitting compressed information. To mitigate the noise from aggressive quantization and the bias from non-IID data, FedCEF integrates a rigorous error feedback mechanism with control variates. Furthermore, we design a communication-efficient pre-proximal downlink strategy that allows clients to exactly reconstruct global control variables without explicit transmission. We theoretically establish that FedCEF achieves sublinear convergence to a bounded residual error under general non-convexity, which is controllable via the step size and batch size. Extensive experiments on real datasets validate FedCEF maintains competitive model accuracy even under extreme compression ratios (e.g., 1%), significantly reducing the total communication volume compared to uncompressed baselines. |
| title | Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2603.07654 |