CTP-FL: Common-Trajectory Gradient Prediction for Federated Learning

arXiv:2609.35130 · cs.LG, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Federated Learning — 1× in this paper · explained in 17 episodes

Sources

• Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
• FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
• DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
• Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data
• FedCM: Federated Learning with Client-level Momentum

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks