pfnet-research / einconv
☆46Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for einconv
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆69Updated 3 months ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- ☆31Updated 4 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Optimization with orthogonal constraints and on general manifolds☆126Updated 4 years ago
- PyTorch AutoNEB implementation to identify minimum energy paths, e.g. in neural network loss landscapes☆54Updated 2 years ago
- Code base for SRSGD.☆28Updated 4 years ago
- ☆67Updated 2 years ago
- Percentile computation for pytorch☆20Updated 4 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆36Updated 5 years ago
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆46Updated 3 years ago
- Spectral Tensor Train Parameterization of Deep Learning Layers☆13Updated 3 years ago
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- Convex potential flows☆78Updated 3 years ago
- ☆40Updated 5 years ago
- ☆17Updated 4 years ago
- This repository is no longer maintained. Check☆82Updated 4 years ago
- ☆62Updated 9 months ago
- Experiments with Neural ODEs and Adversarial Attacks☆44Updated 5 years ago
- MintNet: Building Invertible Neural Networks with Masked Convolutions☆39Updated 3 years ago
- Code for paper "Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow"☆18Updated 4 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆142Updated last year
- ☆52Updated 3 months ago
- Code for the paper "Training Binary Neural Networks with Bayesian Learning Rule☆37Updated 2 years ago
- Wavelet Flow: Fast Training of High Resolution Normalizing Flows☆59Updated 3 years ago
- Lua implementation of Entropy-SGD☆81Updated 6 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 5 years ago
- ☆29Updated 3 years ago
- ☆45Updated 5 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated 2 years ago