LeviViana / torchessian
Full loss Hessian spectrum approximation tool.
☆13Updated 5 years ago
Alternatives and similar repositories for torchessian:
Users that are interested in torchessian are comparing it to the libraries listed below
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆145Updated last year
- Limitations of the Empirical Fisher Approximation☆47Updated 3 weeks ago
- Hessian spectral density estimation in TF and Jax☆122Updated 4 years ago
- This repository is no longer maintained. Check☆81Updated 4 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆74Updated 8 months ago
- ☆28Updated 3 years ago
- Easy-to-use AdaHessian optimizer (PyTorch)☆77Updated 4 years ago
- an implementation of L0 regularization with PyTorch☆57Updated 6 years ago
- ☆83Updated 5 years ago
- Hypergradient descent☆145Updated 10 months ago
- ☆47Updated 5 years ago
- "Layer-wise Adaptive Rate Scaling" in PyTorch☆86Updated 4 years ago
- ☆157Updated 2 years ago
- Pytorch implementation of Variational Dropout Sparsifies Deep Neural Networks☆83Updated 3 years ago
- ☆99Updated 3 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆103Updated 5 years ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated 2 years ago
- ☆189Updated 4 years ago
- Optimization with orthogonal constraints and on general manifolds☆128Updated 4 years ago
- Code for: Implicit Competitive Regularization in GANs☆114Updated 3 years ago
- ☆21Updated 5 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆141Updated 10 months ago
- 🧀 Pytorch code for the Fromage optimiser.☆123Updated 8 months ago
- Convolutional Neural Tangent Kernel☆110Updated 5 years ago
- ☆15Updated 4 years ago
- ☆53Updated 8 months ago
- ☆68Updated 2 years ago
- [ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, …☆167Updated 3 years ago
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 5 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago