beer

Optimization framework

A collection of numerical experiments and code for demonstrating the performance of decentralized nonconvex optimization methods

This repository contains numerical experiments for "BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression"

GitHub

8 stars
1 watching
2 forks
Language: Jupyter Notebook
last commit: almost 2 years ago

Related projects:

Repository Description Stars
clementfarabet/lbfgs An interface to a library providing a quasi-newton method for optimization problems 2
fpicetti/occamypy A library for solving large-scale optimization problems with flexible and scalable vector and operator definitions 54
xidongwu/federated-minimax-and-conditional-stochastic-optimization This project presents optimization techniques for federated learning and minimax games in the context of machine learning 0
srendle/libfm Software implementation of an optimization algorithm used in collaborative filtering and recommender systems 1,488
perone/pyevolve A Python-based optimization framework providing tools and algorithms to evolve solutions from problem definitions. 315
yaodongyu/tct An approach to train and optimize machine learning models in a decentralized setting by convexifying the optimization process 4
hiroyuki-kasai/gdlibrary A collection of unconstrained optimization algorithms implemented in MATLAB 65
jungtaekkim/bayeso A framework for optimizing hyperparameters in machine learning models using Bayesian optimization 93
automl/robo A Bayesian optimization framework designed to optimize complex functions with robustness and flexibility 483
leonardgoeke/anymod.jl A Julia framework for creating large-scale linear optimization models of energy system capacity expansion with multiple periods 70
c-bata/goptuna A decentralized hyperparameter optimization framework inspired by Optuna. 261
jonfanlab/glonet A software framework for training neural networks to optimize dielectric metasurfaces using physics-driven generative models and global optimization algorithms. 101
cicirello/chips-n-salsa A Java library of algorithms and data structures for optimization problems 60
google/ceviche-challenges A software suite for benchmarking photonic inverse design optimization algorithms 94
mysteryresearcher/dasha A framework for distributed optimization with communication compression and optimal oracle complexity. 0