Sharp-Bounds-for-FedAvg-and-Continuous-Perspective
by hongliny
AI summary
Federated Bounds
This project provides mathematical bounds on the performance of Federated Averaging algorithms with Local SGD and Continuous Perspective
- stars
- 4
- forks
- 0
- watching
- 2
Similar projects
Found by comparing what the projects do, not just their names.
Federated learner
Provides code for a federated learning algorithm to optimize machine learning models in a distributed setting.
Federated Optimization Library
This code repository provides an implementation of Federated Composite Optimization for decentralized machine learning
Optimization framework
This project presents optimization techniques for federated learning and minimax games in the context of machine learning
Federated learning system
An implementation of federated submodel averaging (FedSubAvg) to enable collaborative learning across decentralized devices or users.
Federated learner
An implementation of a federated learning algorithm for handling heterogeneous data
Federated Learning Framework
Develops a framework to balance competing goals in federated learning by decoupling generic and personalized prediction tasks.
Federated Image Segmentation Framework
This project presents a framework for federated domain generalization in medical image segmentation using continuous frequency space and episodic learning.
Federated Learning Algorithm
This project presents an approach to federated learning with partial client participation by optimizing anchor selection for improving model accuracy and convergence.
Federated Learning Analysis
Analyzes convergence of sequential federated learning on heterogeneous data using Jupyter Notebook
Federated Learning Study
The purpose of this project is to investigate the convergence of a federated learning algorithm on non-IID (non-identically and independently distributed) data.
Segmentation algorithm
Implementations of federated incremental semantic segmentation in PyTorch.
Federated prediction framework
A framework for incorporating uncertainty quantification into federated learning models
Federated learner
Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift
FL analysis
Analyzes Federated Learning with Arbitrary Client Participation using various optimization strategies and datasets.
Heterogeneity fixer
Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation