TCT
Optimization framework
An approach to train and optimize machine learning models in a decentralized setting by convexifying the optimization process
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
4 stars
6 watching
3 forks
Language: Python
last commit: over 3 years agofederated-learningneural-tangent-kerneloptimization
Related projects:
| Repository | Description | Stars |
|---|---|---|
 xidongwu/federated-minimax-and-conditional-stochastic-optimization | This project presents optimization techniques for federated learning and minimax games in the context of machine learning | 1 |
 jonfanlab/glonet | A software framework for training neural networks to optimize dielectric metasurfaces using physics-driven generative models and global optimization algorithms. | 101 |
 kai-yue/ntk-fed | A framework for federated learning that leverages the neural tangent kernel to address statistical heterogeneity in distributed machine learning. | 3 |
 jiangoforit/yellowfin_pytorch | An optimizer that automatically tunes momentum and learning rate using local quadratic approximation. | 287 |
 hui-po-wang/progfed | An approach to efficient federated learning by progressively training models on client devices with reduced communication and computation requirements. | 20 |
 jungtaekkim/bayeso | A framework for optimizing hyperparameters in machine learning models using Bayesian optimization | 93 |
 alshedivat/fedpa | A modular JAX implementation of federated learning via posterior averaging for decentralized optimization | 50 |
 guopengf/auto-fedrl | A reinforcement learning-based framework for optimizing hyperparameters in distributed machine learning environments. | 15 |
 liboyue/beer | A collection of numerical experiments and code for demonstrating the performance of decentralized nonconvex optimization methods | 8 |
 deng-cy/deep_learning_topology_opt | Optimization code for topology optimization problems using machine learning and deep learning techniques | 107 |
 yh-yao/fedgcn | An implementation of a federated learning algorithm for training Graph Convolutional Networks on semi-supervised node classification tasks. | 59 |
 qinbinli/moon | A framework for collaborative machine learning model training that leverages similarity between model representations to correct local training. | 267 |
 zackzikaixiao/fedgrab | A tool for training federated learning models with adaptive gradient balancing to handle class imbalance in multi-client scenarios. | 14 |
 fpicetti/occamypy | A library for solving large-scale optimization problems with flexible and scalable vector and operator definitions | 55 |
 hongyouc/fed-rod | Develops a framework to balance competing goals in federated learning by decoupling generic and personalized prediction tasks. | 14 |