opooladz / Preconditioned-Stochastic-Gradient-DescentLinks
A repo based on XiLin Li's PSGD repo that extends some of the experiments.
☆14Updated 7 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:
- ☆17Updated 9 months ago
- A State-Space Model with Rational Transfer Function Representation.☆78Updated last year
- ☆61Updated 6 months ago
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆81Updated last year
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆29Updated 4 years ago
- ☆19Updated 2 months ago
- ☆31Updated last year
- ☆53Updated 8 months ago
- [ICML 2024] SIRFShampoo: Structured inverse- and root-free Shampoo in PyTorch (https://arxiv.org/abs/2402.03496)☆14Updated 7 months ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆63Updated last month
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆56Updated 2 weeks ago
- Maximal Update Parametrization (μP) with Flax & Optax.☆11Updated last year
- ☆185Updated 6 months ago
- JAX Implementation of Black Forest Labs' Flux.1 family of models☆33Updated 7 months ago
- ☆33Updated 8 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆88Updated 11 months ago
- Implementation of Diffusion Transformers and Rectified Flow in Jax☆23Updated 10 months ago
- ☆32Updated 8 months ago
- supporting pytorch FSDP for optimizers☆79Updated 5 months ago
- The accompanying code for "Simplifying and Understanding State Space Models with Diagonal Linear RNNs" (Ankit Gupta, Harsh Mehta, Jonatha…☆21Updated 2 years ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆77Updated 10 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆100Updated 5 months ago
- A system for automating selection and optimization of pre-trained models from the TAO Model Zoo☆25Updated 11 months ago
- ☆19Updated 2 weeks ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆175Updated last week
- Official code for Long Expressive Memory (ICLR 2022, Spotlight)☆69Updated 3 years ago
- Utilities for PyTorch distributed☆24Updated 3 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆124Updated last year