torchjd is an open-source Python library that implements Jacobian Descent optimization techniques for use with PyTorch. It provides researchers and developers with tools to apply advanced optimization algorithms in their machine learning workflows, supporting efficient model training and experimentation.
torchjd sits in PulseGate's Infrastructure & Backend category. It enables efficient Jacobian Descent optimization for machine learning models in PyTorch. torchjd is an open-source project aimed at machine learning researchers and developers. The project is open source (Open Source). torchjd is available on the web and the command line.
Behind torchjd is SimplexLab, and the product first shipped in 2024. The project is developed in the open on GitHub with 328 stars and 79 commits in the last 90 days. Among its 5 catalogued features are jacobian descent, pyTorch integration, and optimization algorithms.
Latest indexed changes and source events
Other apps tracked under the same category.
