google-deepmind / dksLinks
Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.
☆70Updated last week
Alternatives and similar repositories for dks
Users that are interested in dks are comparing it to the libraries listed below
Sorting:
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆175Updated last week
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆44Updated 2 years ago
- Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).☆110Updated 3 years ago
- ☆60Updated 3 years ago
- A collection of optimizers, some arcane others well known, for Flax.☆29Updated 3 years ago
- Experiment of using Tangent to autodiff triton☆79Updated last year
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Open source code for EigenGame.☆30Updated 2 years ago
- ☆53Updated 8 months ago
- A port of muP to JAX/Haiku☆25Updated 2 years ago
- Neural Networks for JAX☆84Updated 8 months ago
- ☆33Updated 2 years ago
- JAX implementation of Learning to learn by gradient descent by gradient descent☆27Updated 7 months ago
- ☆114Updated this week
- Latent Diffusion Language Models☆68Updated last year
- JMP is a Mixed Precision library for JAX.☆199Updated 4 months ago
- code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"☆26Updated 2 years ago
- Transformers with doubly stochastic attention☆45Updated 2 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆88Updated 11 months ago
- A selection of neural network models ported from torchvision for JAX & Flax.☆44Updated 4 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆81Updated last year
- Official repository for our ICLR 2021 paper Evaluating the Disentanglement of Deep Generative Models with Manifold Topology☆36Updated 4 years ago
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆31Updated last year
- A simple library for scaling up JAX programs☆137Updated 7 months ago
- ☆32Updated 8 months ago
- ☆104Updated 11 months ago
- Image augmentation library for Jax☆39Updated last year
- ☆31Updated last month
- ☆20Updated last year