fmeirinhos / pytorch-hessianfree
PyTorch implementation of Hessian Free optimisation
☆43Updated 4 years ago
Related projects: ⓘ
- Adaptive gradient descent without descent☆44Updated 2 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.☆68Updated last month
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆125Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆141Updated 11 months ago
- ☆35Updated this week
- Monotone operator equilibrium networks☆51Updated 4 years ago
- paper lists and information on mean-field theory of deep learning☆75Updated 5 years ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- ☆65Updated 5 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆139Updated last year
- Convex potential flows☆78Updated 2 years ago
- PyTorch implementation of FIM and empirical FIM☆57Updated 6 years ago
- ☆56Updated last year
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆34Updated 5 years ago
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 3 years ago
- Deep Neural Networks Entropy from Replicas☆31Updated 4 years ago
- Experiments with Neural ODEs and Adversarial Attacks☆44Updated 5 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 4 years ago
- Hessian spectral density estimation in TF and Jax☆112Updated 4 years ago
- Code for Global Convergence of Block Coordinate Descent in Deep Learning (ICML 2019)☆34Updated 5 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- ☆31Updated 3 years ago
- Optimization with orthogonal constraints and on general manifolds☆123Updated 4 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated last year
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- Convolutional Neural Tangent Kernel☆108Updated 4 years ago
- ☆44Updated 10 months ago
- Code for Non-convex Learning via Replica Exchange Stochastic Gradient MCMC, ICML 2020.☆23Updated 3 years ago
- ☆36Updated 3 years ago