kazukiosawa / ngd_in_wide_nnLinks
simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-space (by empirical/analytical NTK).
☆14Updated 4 years ago
Alternatives and similar repositories for ngd_in_wide_nn
Users that are interested in ngd_in_wide_nn are comparing it to the libraries listed below
Sorting:
- ☆80Updated 3 years ago
- [NeurIPS'19] Deep Equilibrium Models Jax Implementation☆40Updated 4 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆20Updated 3 years ago
- CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.☆78Updated last year
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆87Updated 2 years ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- Models and code for the ICLR 2020 workshop paper "Towards Understanding Normalization in Neural ODEs"☆16Updated 5 years ago
- ☆170Updated last year
- Official code for UnICORNN (ICML 2021)☆28Updated 3 years ago
- Bayesian algorithm execution (BAX)☆50Updated 3 years ago
- Monotone operator equilibrium networks☆53Updated 5 years ago
- Code for efficiently sampling functions from GP(flow) posteriors☆73Updated 4 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated 5 months ago
- Neural likelihood-free methods in PyTorch.☆39Updated 5 years ago
- Hessian spectral density estimation in TF and Jax☆123Updated 4 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 5 years ago
- Demos for the paper Generalized Variational Inference (Knoblauch, Jewson & Damoulas, 2019)☆20Updated 6 years ago
- Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight☆53Updated 3 years ago
- Code repo for "Function-Space Distributions over Kernels"☆32Updated 4 years ago
- Normalizing Flows using JAX☆84Updated last year
- Probabilistic Solution of Differential Equations☆13Updated 3 years ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated 2 years ago
- Adaptive gradient descent without descent☆48Updated 3 years ago
- ☆52Updated 2 years ago
- repo for paper: Adaptive Checkpoint Adjoint (ACA) method for gradient estimation in neural ODE☆56Updated 4 years ago
- ☆30Updated 11 months ago
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- [ICLR 2022] Path integral sampler☆50Updated 2 years ago
- A small library for creating and manipulating custom JAX Pytree classes☆56Updated 2 years ago
- code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"☆26Updated 2 years ago