paper-with-me

Papers

Safe-EF: Error Feedback for Nonsmooth Constrained Optimization

2025-05-09 · Rustem Islamov, Yarden As, Ilyas Fatkhullin

Federated learning faces severe communication bottlenecks due to the high dimensionality of model updates. Communication compression with contractive compressors (e.g., Top-K) is often preferable in practice but can degrade performance without proper handling. Error feedback (EF) mitigates such issues but has been largely restricted for smooth, unconstrained problems, limiting its real-world applicability where non-smooth objectives and safety constraints are critical. We advance our understanding of EF in the canonical non-smooth convex setting by establishing new lower complexity bounds for first-order algorithms with contractive compression. Next, we propose Safe-EF, a novel algorithm that matches our lower bound (up to a constant) while enforcing safety constraints essential for practical applications. Extending our approach to the stochastic setting, we bridge the gap between theory and practical implementation. Extensive experiments in a reinforcement learning setup, simulating distributed humanoid robot training, validate the effectiveness of Safe-EF in ensuring safety and reducing communication complexity.

📄 PDF Abstract BibTeX arXiv:2505.06053

Code (1)

yardenas/safe-ef 공식 구현 jax

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Certified Gradient-Based Contact-Rich Manipulation via Smoothing-Error Reachable Tubes

2026-02-10 · Wei-Chen Li, Glen Chou arxiv

Gradient-based methods can efficiently optimize controllers by leveraging differentiable simulation and physical priors. However, contact-rich manipulation remains challenging because hybrid contact dynamics often produc…

Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential

2022-10-20 · Xingang Guo, Bin Hu

Direct policy search has been widely applied in modern reinforcement learning and continuous control. However, the theoretical properties of direct policy search on nonsmooth robust control synthesis have not been fully …

continuous-controlContinuous Control

Primal-Dual Methods for Nonsmooth Nonconvex Optimization with Orthogonality Constraints

2026-04-05 · Linglingzhi Zhu, Wentao Ding, Shangyuan Liu, Anthony Man-Cho So arxiv

Recent advancements in data science have significantly elevated the importance of orthogonally constrained optimization problems. The Riemannian approach has become a popular technique for addressing these problems due t…

Computational Efficiency

Offline Safe Policy Optimization From Heterogeneous Feedback

2025-12-23 · Ze Gong, Pradeep Varakantham, Akshat Kumar arxiv

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, e…

Reinforcement LearningContinuous Control

The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach

2023-02-16 · Yongcun Song, Xiaoming Yuan, Hangrui Yue

We study the combination of the alternating direction method of multipliers (ADMM) with physics-informed neural networks (PINNs) for a general class of nonsmooth partial differential equation (PDE)-constrained optimizati…