Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

arXiv:2311.03154 · cs.LG · Submitted 2023-11-06 · Read on arXiv

cs.LG

Submitted: 2023-11-06

Updated: 2026-09-14

Comments: Accepted at NeurIPS 2023. arXiv admin note: text overlap with arXiv:2302.01633

Code: https://github.com/liyipeng00/convergence

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 117× in this paper · explained in 1 episode
• Federated Learning — 22× in this paper · explained in 14 episodes
• Convergence Guarantees — 11× in this paper · explained in 3 episodes
• Objective Function — 10× in this paper · explained in 2 episodes
• Data Heterogeneity — 8× in this paper · explained in 3 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Federated Learning (FL) — 3× in this paper · explained in 7 episodes
• Sequential Split Learning — 3× in this paper
• Stochastic Gradient Descent — 3× in this paper
• Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Non-IID Data — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Multi-Layer Perceptron — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Federated Learning Based on Dynamic Regularization
• Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
• On the Convergence of Federated Averaging with Cyclic Client Participation
• CINIC-10 is not ImageNet or CIFAR-10
• Handbook of Convergence Theorems for (Stochastic) Gradient Methods
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Federated Learning with Regularized Client Participation
• Online Learning: A Modern Introduction Using Convex Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unified Optimal Analysis of the (Stochastic) Gradient Method
• The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication
• On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization
• On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks