tyohei / chainerkfacLinks
A Chainer extension for K-FAC
☆20Updated 6 years ago
Alternatives and similar repositories for chainerkfac
Users that are interested in chainerkfac are comparing it to the libraries listed below
Sorting:
- Limitations of the Empirical Fisher Approximation☆49Updated 10 months ago
- ☆83Updated 6 years ago
- Regularization, Neural Network Training Dynamics☆14Updated 6 years ago
- Lua implementation of Entropy-SGD☆81Updated 7 years ago
- This repository is no longer maintained. Check☆81Updated 5 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆150Updated 2 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 7 years ago
- hessian in pytorch☆187Updated 5 years ago
- Code for "Accelerating Natural Gradient with Higher-Order Invariance"☆30Updated 6 years ago
- ☆77Updated 6 years ago
- Convolutional Neural Tangent Kernel☆112Updated 6 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆113Updated 5 years ago
- Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)☆142Updated 6 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆36Updated 5 years ago
- Hypergradient descent☆147Updated last year
- SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning☆23Updated 7 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆61Updated 6 years ago
- ☆135Updated 8 years ago
- Implementation of the Deep Frank-Wolfe Algorithm -- Pytorch☆63Updated 4 years ago
- Computing various norms/measures on over-parametrized neural networks☆50Updated 7 years ago
- ☆26Updated 6 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- Implementation of Information Dropout☆39Updated 8 years ago
- This project is the Torch implementation of our accepted AAAI 2018 paper : orthogonal weight normalization method for solving orthogonali…☆57Updated 6 years ago
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 6 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆148Updated 2 years ago
- The Singular Values of Convolutional Layers☆72Updated 7 years ago
- ☆126Updated last year
- ☆47Updated 6 years ago