jotaf98 / pytorch-curveball
A second-order optimizer for deep networks
☆24Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for pytorch-curveball
- An Implementation of "Small steps and giant leaps: Minimal Newton solvers for Deep Learning" In pytorch☆21Updated 6 years ago
- This repository is no longer maintained. Check☆82Updated 4 years ago
- (Batched) advanced indexing for PyTorch.☆53Updated 11 months ago
- ☆40Updated last year
- Percentile computation for pytorch☆20Updated 4 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆39Updated 4 years ago
- An implementation of shampoo☆74Updated 6 years ago
- Masked Convolutional Flow☆59Updated 4 years ago
- ☆61Updated 4 years ago
- Implementation of the reversible residual network in pytorch☆101Updated 2 years ago
- ☆27Updated 4 years ago
- ☆31Updated 4 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- A pytorch implementation of Information Bottleneck GAN☆28Updated 5 years ago
- Recurrent Back Propagation, Back Propagation Through Optimization, ICML 2018☆39Updated 5 years ago
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆69Updated 4 months ago
- A PyTorch implementation of Conditional PixelCNNs☆27Updated 6 years ago
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated last year
- ☆34Updated 5 years ago
- The Deep Weight Prior, ICLR 2019☆44Updated 3 years ago
- Efficient reservoir sampling implementation for PyTorch☆104Updated 3 years ago
- Matrix square root with gradient support for PyTorch☆64Updated 2 years ago
- ☆37Updated 5 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- The Limited Multi-Label Projection Layer☆57Updated 4 months ago
- Like Moving MNIST, but way more flexible☆24Updated 4 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 5 years ago
- Reference implementation of the PAL optimizer☆20Updated 4 years ago