g-benton / loss-surface-simplexes
ā99Updated 3 years ago
Alternatives and similar repositories for loss-surface-simplexes:
Users that are interested in loss-surface-simplexes are comparing it to the libraries listed below
- Hessian spectral density estimation in TF and Jaxā123Updated 4 years ago
- ā53Updated 8 months ago
- š§ Pytorch code for the Fromage optimiser.ā123Updated 9 months ago
- A library for evaluating representations.ā76Updated 3 years ago
- A Machine Learning workflow for Slurm.ā149Updated 4 years ago
- Codebase for Learning Invariances in Neural Networksā94Updated 2 years ago
- Discrete Normalizing Flows implemented in PyTorchā112Updated 3 years ago
- Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"ā33Updated 2 years ago
- Bayesianize: A Bayesian neural network wrapper in pytorchā88Updated 11 months ago
- Last-layer Laplace approximation code examplesā83Updated 3 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorchā145Updated last year
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"ā44Updated 4 years ago
- Monotone operator equilibrium networksā51Updated 4 years ago
- Differentiable Sorting Networksā114Updated last year
- ā29Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"ā106Updated 4 years ago
- Riemannian Convex Potential Mapsā67Updated 2 years ago
- Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard ā¦ā39Updated 4 years ago
- ā64Updated last year
- Stochastic Automatic Differentiation library for PyTorch.ā198Updated 7 months ago
- š© Pytorch and Jax code for the Madam optimiser.ā51Updated 4 years ago
- Code for the Thermodynamic Variational Objectiveā26Updated 2 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.ā75Updated 8 months ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)ā61Updated 3 years ago
- Normalizing Flows using JAXā83Updated last year
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"ā40Updated 2 years ago
- ā18Updated last year
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We sā¦ā67Updated 2 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)ā36Updated last month
- Reparameterize your PyTorch modulesā71Updated 4 years ago