umutsimsekli / sgd_tail_indexLinks
The codebase for the paper "A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks"
☆25Updated 5 years ago
Alternatives and similar repositories for sgd_tail_index
Users that are interested in sgd_tail_index are comparing it to the libraries listed below
Sorting:
- NTK reading group☆87Updated 5 years ago
- Convolutional Neural Tangent Kernel☆113Updated 5 years ago
- paper lists and information on mean-field theory of deep learning☆78Updated 6 years ago
- ☆59Updated 2 years ago
- Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)☆140Updated 6 years ago
- Testing Nerual Tangent Kernel (NTK) on small UCI datasets☆81Updated 5 years ago
- ☆152Updated 5 years ago
- The collection of recent papers about variational inference☆85Updated 5 years ago
- Implementation of the variational continual learning method☆191Updated 6 years ago
- ☆67Updated 6 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆176Updated 5 years ago
- ☆157Updated 3 years ago
- PyTorch implementation of "Weight Uncertainty in Neural Networks"☆176Updated 3 years ago
- Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)☆86Updated 5 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆375Updated last year
- ☆91Updated 3 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆100Updated 6 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆144Updated 2 years ago
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks☆19Updated 6 years ago
- demonstration of the information bottleneck theory for deep learning☆64Updated 7 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 5 years ago
- Hypergradient descent☆149Updated last year
- Repository for theory and methods for Out-of-Distribution (OoD) generalization☆63Updated 3 years ago
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆56Updated 5 years ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆33Updated 2 years ago
- hessian in pytorch☆187Updated 4 years ago
- computation of convolutional kernels (CKN and NTK) in C++☆14Updated 2 years ago
- Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning☆92Updated 4 years ago
- PyTorch implementation for the ICLR 2020 paper "Understanding the Limitations of Variational Mutual Information Estimators"☆74Updated 5 years ago