f-dangel / hbp
Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations
☆20Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hbp
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- ☆46Updated 5 years ago
- ☆31Updated 4 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆69Updated 3 months ago
- PyTorch implementation of Hessian Free optimisation☆43Updated 4 years ago
- ☆52Updated 3 months ago
- Stochastic Gradient Langevin Dynamics for Bayesian learning☆30Updated 2 years ago
- Simple and extensible hypergradient for PyTorch☆16Updated last year
- Distributed K-FAC Preconditioner for PyTorch☆80Updated this week
- Adaptive gradient descent without descent☆44Updated 3 years ago
- Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561☆25Updated 3 years ago
- Hessian trace estimation using PyTorch and Hutch++☆19Updated 4 years ago
- Code for Knowledge-Adaptation Priors based on the NeurIPS 2021 paper by Khan and Swaroop.☆16Updated 2 years ago
- Regularization, Neural Network Training Dynamics☆14Updated 4 years ago
- Code for "Accelerating Natural Gradient with Higher-Order Invariance"☆30Updated 5 years ago
- scipy linear operators for the Hessian, Fisher/GGN, and more in PyTorch☆18Updated 2 weeks ago
- Code accompanying VarGrad: A Low-Variance Gradient Estimator for Variational Inference☆12Updated 4 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆17Updated 2 years ago
- A minimal implementation of a VAE with BinConcrete (relaxed Bernoulli) latent distribution in TensorFlow.☆21Updated 4 years ago
- Code for the Thermodynamic Variational Objective☆26Updated 2 years ago
- Euclidean Wasserstein-2 optimal transportation☆44Updated last year
- Relative gradient optimization of the Jacobian term in unsupervised deep learning, NeurIPS 2020☆21Updated 3 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
- ☆49Updated 4 years ago
- Code for "Exponential Family Estimation via Adversarial Dynamics Embedding" (NeurIPS 2019)☆13Updated 4 years ago
- Hessian spectral density estimation in TF and Jax☆115Updated 4 years ago
- ☆47Updated 3 months ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago