TorchJD / torchjdLinks
Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
☆298Updated this week
Alternatives and similar repositories for torchjd
Users that are interested in torchjd are comparing it to the libraries listed below
Sorting:
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆434Updated last year
- ☆246Updated last year
- optimizer & lr scheduler & loss function collections in PyTorch☆388Updated last week
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆352Updated 2 months ago
- TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conte…☆124Updated 11 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Reliable, minimal and scalable library for pretraining foundation and world models☆126Updated this week
- Efficient optimizers☆281Updated last month
- Code for our NeurIPS 2022 paper☆371Updated 3 years ago
- ☆123Updated 7 months ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- Load tensorboard event logs as pandas DataFrames for scientific plotting; Supports both PyTorch and TensorFlow☆208Updated last year
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated 2 years ago
- Modern Fixed Point Systems using Pytorch☆127Updated 2 years ago
- Universal Notation for Tensor Operations in Python.☆469Updated 10 months ago
- ☆215Updated last year
- D-Adaptation for SGD, Adam and AdaGrad☆528Updated last year
- A general-purpose, deep learning-first library for constrained optimization in PyTorch☆152Updated 2 months ago
- Minimal Implementation of a D3PM in pytorch☆285Updated last year
- Normalizing flows in PyTorch☆442Updated 2 months ago
- Easy Hypernetworks in Pytorch and Jax☆106Updated 3 years ago