nevergrad
Optimizer
A Python toolbox for performing optimization of complex functions without explicit gradient calculation.
A Python toolbox for performing gradient-free optimization
4k stars
58 watching
356 forks
Language: Python
last commit: 3 months ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
| A comprehensive framework for solving optimization problems without gradient calculations. | 575 |
| Automatically computes derivatives of Python and NumPy code for optimization tasks | 7,049 |
| An autograd engine for textual gradients using large language models to backpropagate gradients. | 1,912 |
| A reinforcement learning environment library for compiler optimization tasks | 917 |
| A Matlab toolbox providing a generic solver for proximal gradient descent in convex and non-convex optimization problems with various regularization terms. | 49 |
| An optimizer that combines the benefits of Adam and SGD algorithms | 2,908 |
| PyTorch implementation of a technique to improve the interpretability of deep learning models by adding noise to the gradients | 168 |
| A Python library implementing a machine learning boosting framework with probabilistic prediction capabilities | 1,663 |
| A software framework for training neural networks to optimize dielectric metasurfaces using physics-driven generative models and global optimization algorithms. | 101 |
| A high-performance gradient boosting framework for machine learning tasks | 16,769 |
| An optimized distributed gradient boosting library designed to be highly efficient and flexible | 26,396 |
| A Python-based package for solving optimization problems in power systems | 135 |
| A collection of unconstrained optimization algorithms implemented in MATLAB | 67 |
| A software toolkit implementing a novel reinforcement learning framework for portfolio management with policy optimization and financial-model-based algorithms. | 1,755 |
| PyTorch implementation of Noisy Natural Gradient as Variational Inference for Bayesian Neural Networks | 121 |