opooladz / Preconditioned-Stochastic-Gradient-DescentLinks
A repo based on XiLin Li's PSGD repo that extends some of the experiments.
☆14Updated 11 months ago
Alternatives and similar repositories for Preconditioned-Stochastic-Gradient-Descent
Users that are interested in Preconditioned-Stochastic-Gradient-Descent are comparing it to the libraries listed below
Sorting:
- ☆67Updated 10 months ago
- ☆215Updated 10 months ago
- supporting pytorch FSDP for optimizers☆84Updated 9 months ago
- ☆17Updated last year
- A State-Space Model with Rational Transfer Function Representation.☆81Updated last year
- ☆19Updated 4 months ago
- ☆58Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆91Updated last year
- ☆34Updated last year
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆70Updated last month
- Supporting code for the blog post on modular manifolds.☆39Updated last week
- ☆34Updated last year
- ☆40Updated 3 weeks ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆97Updated 2 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆183Updated last week
- Focused on fast experimentation and simplicity☆75Updated 9 months ago
- Implementation of Diffusion Transformers and Rectified Flow in Jax☆25Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 9 months ago
- Scalable and Stable Parallelization of Nonlinear RNNS☆22Updated last month
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Updated last year
- ☆120Updated 3 months ago
- Efficient optimizers☆265Updated last week
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆66Updated last month
- ☆32Updated last year
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆29Updated 5 years ago
- ☆53Updated last year
- FID computation in Jax/Flax.☆28Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 3 years ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆63Updated 2 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year