f-dangel / singdLinks
[ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
☆22Updated 7 months ago
Alternatives and similar repositories for singd
Users that are interested in singd are comparing it to the libraries listed below
Sorting:
- ☆16Updated 2 years ago
- [TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivative…☆17Updated last year
- [ICML 2024] SIRFShampoo: Structured inverse- and root-free Shampoo in PyTorch (https://arxiv.org/abs/2402.03496)☆14Updated 7 months ago
- ☆53Updated 8 months ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆38Updated last month
- ☆32Updated 8 months ago
- Transformers with doubly stochastic attention☆45Updated 2 years ago
- Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.☆25Updated last year
- ☆17Updated 11 months ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆75Updated 10 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 11 months ago
- ☆10Updated last month
- Convolutions and more as einsum for PyTorch☆16Updated last year
- Laplace approximated BNN surrogate for BoTorch☆8Updated 6 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆175Updated this week
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆41Updated 2 years ago
- ☆51Updated 11 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- ☆12Updated 2 years ago
- code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"☆26Updated 2 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆45Updated 4 years ago
- ☆41Updated 2 years ago
- Visualization of mean field and neural tangent kernel regime☆20Updated 10 months ago
- Supporing code for the paper "Bayesian Model Selection, the Marginal Likelihood, and Generalization".☆35Updated 2 years ago
- ☆33Updated 2 years ago