f-dangel / singdLinks
[ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
☆22Updated 10 months ago
Alternatives and similar repositories for singd
Users that are interested in singd are comparing it to the libraries listed below
Sorting:
- [TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivative…☆17Updated 2 years ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆180Updated this week
- ☆57Updated 11 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated 11 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated last year
- ☆51Updated last year
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- Transformers with doubly stochastic attention☆47Updated 3 years ago
- Open source code for EigenGame.☆30Updated 2 years ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆38Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 3 years ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- ☆17Updated last year
- ☆33Updated 2 years ago
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆72Updated 2 months ago
- Distributed K-FAC preconditioner for PyTorch☆90Updated this week
- Efficient Householder Transformation in PyTorch☆66Updated 4 years ago
- ☆12Updated 3 years ago
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆63Updated 2 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆189Updated 9 months ago
- TensorLy-Torch: Deep Tensor Learning with TensorLy and PyTorch☆80Updated last year
- If it quacks like a tensor...☆59Updated 10 months ago
- ☆39Updated 2 weeks ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- Blog post☆17Updated last year
- Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).☆112Updated 3 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 2 years ago
- Easy-to-use AdaHessian optimizer (PyTorch)☆79Updated 4 years ago