Updated 6 months ago

irace • Rank 17.1 • Science 49%

Iterated Racing for Automatic Algorithm Configuration

Updated 5 months ago

SDMtune • Rank 11.1 • Science 26%

Performs Variables selection and model tuning for Species Distribution Models (SDMs). It provides also several utilities to display results.

Updated 5 months ago

https://github.com/grailbio/diviner • Rank 4.7 • Science 13%

Diviner is a serverless machine learning and hyper parameter tuning platform

Updated 5 months ago

https://github.com/ai-team-uoa/autoer • Science 26%

Code & Experiments for IEEE Access paper "Auto-Configuring Entity Resolution Pipelines" by K.Nikoletos, V.Efthymiou, G.Papadakis and K.Stafanidis

Updated 6 months ago

dpl • Science 44%

[NeurIPS 2023] Multi-fidelity hyperparameter optimization with deep power laws that achieves state-of-the-art results across diverse benchmarks.

Updated 6 months ago

mlp_hpp_analysis • Science 57%

This repository is the code basis for the paper intitled "Exploring the Intricacies of Neural Network Optimization"

Updated 6 months ago

syne-tune • Science 54%

Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.

Updated 6 months ago

rapidx • Science 44%

A toolbox that integrates with PyTorch-Lightning which helps in running and managing multiple codebases

Updated 5 months ago

https://github.com/copyleftdev/tundr • Science 36%

A high-performance optimization server implementing the Model Context Protocol (MCP) for mathematical optimization tasks, with a focus on Bayesian Optimization using Gaussian Processes. Designed for reliability, scalability, and ease of integration in production environments.

Updated 6 months ago

propulate • Science 75%

Propulate is an asynchronous population-based optimization algorithm and software package for global optimization and hyperparameter search on high-performance computers.

Updated 5 months ago

https://github.com/cmower/hyparam • Science 23%

Container for hyper parameter tuning in machine learning.

Updated 6 months ago

agilerl • Science 54%

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.