stochastic adaptive cubic regularization method with negative curvature
-
Updated
May 7, 2020 - Python
stochastic adaptive cubic regularization method with negative curvature
This project implements cubic regularization optimization algorithms and related methods for machine learning, with a focus on robust and efficient training. It includes modular Python code for data handling, experiment management, and various optimizers, along with scripts and visualizations for benchmarking on standard datasets.
Adaptive Regularization with Cubics (ARC) optimizer for PyTorch.
To associate your repository with the cubic-regularization topic, visit your repo's landing page and select "manage topics."