f-dangel / singdLinks
[ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
☆22Updated 9 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…☆179Updated last week
- ☆56Updated 10 months ago
- Transformers with doubly stochastic attention☆47Updated 2 years ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆126Updated last year
- ☆33Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated 11 months ago
- Layerwise Batch Entropy Regularization☆23Updated 3 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
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- Open source code for EigenGame.☆30Updated 2 years ago
- ☆11Updated 4 months ago
- ☆51Updated last year
- ☆37Updated 2 weeks ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆189Updated 8 months ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆27Updated last year
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆71Updated 2 months ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- Implementation of LogAvgExp for Pytorch☆36Updated 4 months ago
- ☆17Updated last year
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆63Updated 2 years ago
- Distributed K-FAC preconditioner for PyTorch☆89Updated this week
- ☆12Updated 3 years ago
- Efficient Householder Transformation in PyTorch☆66Updated 4 years ago
- ☆32Updated 10 months ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆42Updated 6 years ago
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆89Updated 2 years ago