wiseodd / natural-gradientsLinks
Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)
☆141Updated 6 years ago
Alternatives and similar repositories for natural-gradients
Users that are interested in natural-gradients are comparing it to the libraries listed below
Sorting:
- paper lists and information on mean-field theory of deep learning☆78Updated 6 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆147Updated 2 years ago
- Convolutional Neural Tangent Kernel☆112Updated 6 years ago
- Hypergradient descent☆148Updated last year
- NTK reading group☆87Updated 5 years ago
- ☆124Updated last year
- a python implementation of various versions of the information bottleneck, including automated parameter searching☆128Updated 5 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆100Updated 7 years ago
- hessian in pytorch☆187Updated 4 years ago
- Computing various norms/measures on over-parametrized neural networks☆50Updated 6 years ago
- Limitations of the Empirical Fisher Approximation☆48Updated 7 months ago
- Experiments for the paper "Exponential expressivity in deep neural networks through transient chaos"☆73Updated 9 years ago
- Hessian spectral density estimation in TF and Jax☆124Updated 5 years ago
- ☆154Updated 5 years ago
- ☆67Updated 6 years ago
- Geometric Certifications of Neural Nets☆42Updated 2 years ago
- ☆133Updated 8 years ago
- Code for ICML 2018 paper on "Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam" by Khan, Nielsen, Tangkaratt, Lin, …☆112Updated 6 years ago
- ☆171Updated last year
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆176Updated 5 years ago
- Understanding normalizing flows☆132Updated 5 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆54Updated 6 years ago
- explore DNNs via Infomration☆265Updated 5 years ago
- pyhessian is a TensorFlow module which can be used to estimate Hessian matrices☆24Updated 4 years ago
- ☆157Updated 3 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆147Updated 2 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆104Updated 5 years ago
- ☆26Updated 6 years ago
- Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)☆85Updated 5 years ago
- Testing Nerual Tangent Kernel (NTK) on small UCI datasets☆80Updated 6 years ago