moskomule / hypergrad
Simple and extensible hypergradient for PyTorch
☆16Updated last year
Alternatives and similar repositories for hypergrad:
Users that are interested in hypergrad are comparing it to the libraries listed below
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- Limitations of the Empirical Fisher Approximation☆46Updated 4 years ago
- simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…☆14Updated 4 years ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- Stochastic Gradient Langevin Dynamics for Bayesian learning☆30Updated 3 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated 2 years ago
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆27Updated 3 years ago
- Code accompanying VarGrad: A Low-Variance Gradient Estimator for Variational Inference☆12Updated 4 years ago
- Adaptive gradient descent without descent☆47Updated 3 years ago
- ☆31Updated 4 years ago
- Implementation of the paper "Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory", Ron Amit and Ron Meir, ICML 2018☆17Updated 3 years ago
- Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561☆24Updated 3 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Code for A General Recipe for Likelihood-free Bayesian Optimization, ICML 2022☆44Updated 2 years ago
- Source code for ICLR 2020 paper: "Learning to Guide Random Search"☆39Updated 4 months ago
- ☆28Updated 5 years ago
- Code for Unbiased Implicit Variational Inference (UIVI)☆13Updated 6 years ago
- Implementation of the PAC Bayesian GP learning method.☆10Updated 6 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆56Updated 3 years ago
- Repository for DTU Special Course, focusing on Variational Inference using Normalizing Flows (VINF). Supervised by Michael Riis Andersen☆25Updated 4 years ago
- ☆53Updated 5 months ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight☆52Updated 3 years ago
- [ICLR 2022] Path integral sampler☆43Updated last year
- Code to accompany the paper Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning☆33Updated 4 years ago
- Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"☆33Updated 2 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- ☆35Updated 2 years ago
- ☆15Updated 2 years ago
- An empirical investigation of deep learning theory☆16Updated 5 years ago