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 Understanding and Mitigating Exploding Inverses in Invertible Neural Networks (AISTATS 2021) http://arxiv.org/abs/2006.09347☆30Updated 5 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- ☆47Updated 6 years ago
- Monotone operator equilibrium networks☆53Updated 5 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆88Updated 2 years ago
- Limitations of the Empirical Fisher Approximation☆48Updated 7 months ago
- Relative gradient optimization of the Jacobian term in unsupervised deep learning, NeurIPS 2020☆21Updated 4 years ago
- A differentiation API for PyTorch☆30Updated 5 years ago
- PyTorch implementation of Continuously Indexed Flows paper, with many baseline normalising flows☆31Updated 4 years ago
- PyTorch implementation of Hessian Free optimisation☆43Updated 5 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆57Updated 4 years ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- Convex potential flows☆84Updated 3 years ago
- ☆64Updated last year
- orbital MCMC☆10Updated 4 years ago
- Pytorch implementation of the Power Spherical distribution☆74Updated last year
- ☆54Updated last year
- Simple and extensible hypergradient for PyTorch☆18Updated 2 years ago
- Hessian trace estimation using PyTorch and Hutch++☆19Updated 4 years ago
- ☆15Updated 4 years ago
- Probabilistic Solution of Differential Equations☆13Updated 3 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆131Updated 6 years ago
- ☆30Updated 4 years ago
- Adaptive gradient descent without descent☆48Updated 3 years ago
- Experiment code for "Randomized Automatic Differentiation"☆67Updated 5 years ago
- MintNet: Building Invertible Neural Networks with Masked Convolutions☆39Updated 4 years ago
- Neural likelihood-free methods in PyTorch.☆39Updated 5 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆20Updated 3 years ago
- Efficient Householder Transformation in PyTorch☆66Updated 4 years ago
- ☆170Updated last year