formll / dogLinks
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
☆63Updated 2 years ago
Alternatives and similar repositories for dog
Users that are interested in dog are comparing it to the libraries listed below
Sorting:
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆181Updated this week
- ☆39Updated 2 weeks ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆142Updated last year
- ☆58Updated 11 months ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆63Updated 4 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆88Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 3 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated 11 months ago
- ☆210Updated 9 months ago
- This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classi…☆130Updated 3 years ago
- 🧱 Modula software package☆237Updated last month
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- ☆70Updated 9 months ago
- ☆56Updated 5 months ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆38Updated 2 years ago
- Unofficial implementation of Conformal Language Modeling by Quach et al☆29Updated 2 years ago
- Lightning-like training API for JAX with Flax☆42Updated 9 months ago
- Transformers with doubly stochastic attention☆47Updated 3 years ago
- ☆32Updated 11 months ago
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆22Updated 10 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated last year
- This repository contains PyTorch implementations of various random feature maps for dot product kernels.☆22Updated last year
- ☆119Updated 3 months ago
- Code for the paper "Function-Space Learning Rates"☆23Updated 3 months ago
- ☆38Updated last year
- Pytorch code for experiments on Linear Transformers☆23Updated last year
- Diffusion models in PyTorch☆111Updated this week