FedTorch is a generic repository for benchmarking different federated and distributed learning algorithms using PyTorch Distributed API.
-
Updated
May 2, 2024 - Python
FedTorch is a generic repository for benchmarking different federated and distributed learning algorithms using PyTorch Distributed API.
Distributed Multidisciplinary Design Optimization
Parallel optimizer based on the Global Function Search
Consensus-ADMM for multi-robot trajectory optimization.
Decentralized Sporadic Federated Learning: A Unified Methodology with Generalized Convergence Guarantees
A ray-based library of Distributed POPulation-based OPtimization for Large-Scale Black-Box Optimization.
Sparse Convex Optimization Toolkit (SCOT)
EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization. NeurIPS, 2022
A package for solving optimal power flow problems using distributed algorithms.
DISROPT: A Python framework for distributed optimization
Fair Resource Allocation in Federated Learning (ICLR '20)
Distributed approach of scheduling residential EV charging to maintain reliability of power distribution grids.
The repository focuses on conducting Federated Learning experiments using the Intel OpenFL framework with diverse machine learning models, utilizing image and tabular datasets, applicable different domains like medicine, banking etc.
Code for "A Distributed Buffering Drift-Plus-Penalty Algorithm for Coupling Constrained Optimization" (L-CSS, status: revise and resubmit)
Code for ''Distributed Online Optimization with Coupled Inequality Constraints over Unbalanced Directed Networks'' (CDC 2023)
This repo is an implementation of the algorithm from the paper Consensus on Lie groups for the Riemannian Center of Mass. This algorithm computes the Riemannian center of mass of a set of points in a distributed manner, generalizing the Euclidean average consensus dynamics.
Error feedback based quantization aided and convergence guaranteed Communication Efficient Federated Linear and Deep GCCA
Error feedback based quantization aided and convergence guaranteed Communication Efficient Federated Linear and Deep GCCA
tvopt is a prototyping and benchmarking Python framework for time-varying (or online) optimization.
Add a description, image, and links to the distributed-optimization topic page so that developers can more easily learn about it.
To associate your repository with the distributed-optimization topic, visit your repo's landing page and select "manage topics."