TorchJD / torchjdLinks
Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
☆271Updated last week
Alternatives and similar repositories for torchjd
Users that are interested in torchjd are comparing it to the libraries listed below
Sorting:
- ☆220Updated 10 months ago
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆426Updated 10 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆320Updated 3 months ago
- optimizer & lr scheduler & loss function collections in PyTorch☆368Updated this week
- TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conte…☆121Updated 8 months ago
- Efficient optimizers☆275Updated 2 weeks ago
- Code for our NeurIPS 2022 paper☆369Updated 2 years ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Parameter-Free Optimizers for Pytorch☆131Updated last year
- ☆306Updated 9 months ago
- Modern Fixed Point Systems using Pytorch☆121Updated 2 years ago
- Reliable, minimal and scalable library for pretraining foundation and world models☆73Updated this week
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- ☆150Updated last year
- Normalizing flows in PyTorch☆411Updated 2 weeks ago
- ☆120Updated 4 months ago
- This is the official code release for Bayesian Flow Networks.☆300Updated last year
- For optimization algorithm research and development.☆543Updated last week
- Universal Notation for Tensor Operations in Python.☆442Updated 6 months ago
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆400Updated last week
- Laplace approximations for Deep Learning.☆523Updated 6 months ago
- TorchOpt is an efficient library for differentiable optimization built upon PyTorch.☆615Updated 3 weeks ago
- When it comes to optimizers, it's always better to be safe than sorry☆375Updated last month
- 🧱 Modula software package☆299Updated 2 months ago
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆104Updated 9 months ago
- The boundary of neural network trainability is fractal☆217Updated last year
- Implementation of https://srush.github.io/annotated-s4☆504Updated 4 months ago
- A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...☆376Updated last week
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆494Updated 2 years ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆96Updated 3 months ago