f-dangel / hbpLinks
Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations
☆21Updated 2 years ago
Alternatives and similar repositories for hbp
Users that are interested in hbp are comparing it to the libraries listed below
Sorting:
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- Code accompanying VarGrad: A Low-Variance Gradient Estimator for Variational Inference☆12Updated 5 years ago
- Monotone operator equilibrium networks☆53Updated 5 years ago
- ☆47Updated 6 years ago
- Code for Understanding and Mitigating Exploding Inverses in Invertible Neural Networks (AISTATS 2021) http://arxiv.org/abs/2006.09347☆30Updated 5 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆88Updated 3 years ago
- Hessian trace estimation using PyTorch and Hutch++☆19Updated 4 years ago
- ☆64Updated last year
- Limitations of the Empirical Fisher Approximation☆48Updated 7 months ago
- Convex potential flows☆84Updated 3 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆131Updated 6 years ago
- ☆54Updated last year
- Code for "Accelerating Natural Gradient with Higher-Order Invariance"☆30Updated 6 years ago
- Probabilistic Solution of Differential Equations☆13Updated 3 years ago
- PyTorch implementation of Hessian Free optimisation☆43Updated 5 years ago
- Neural likelihood-free methods in PyTorch.☆39Updated 5 years ago
- Distributed K-FAC preconditioner for PyTorch☆91Updated this week
- PyTorch implementation of Continuously Indexed Flows paper, with many baseline normalising flows☆31Updated 4 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆57Updated 4 years ago
- ☆50Updated 5 years ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- ☆22Updated 3 years ago
- ☆30Updated 4 years ago
- Relative gradient optimization of the Jacobian term in unsupervised deep learning, NeurIPS 2020☆21Updated 4 years ago
- Hessian spectral density estimation in TF and Jax☆124Updated 5 years ago
- code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"☆27Updated 2 years ago
- Pytorch implementation of the Power Spherical distribution☆74Updated last year
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆21Updated 3 years ago
- Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561☆25Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆104Updated 5 years ago