aks2203 / easy-to-hard
Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
☆59Updated 3 years ago
Alternatives and similar repositories for easy-to-hard:
Users that are interested in easy-to-hard are comparing it to the libraries listed below
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 3 years ago
- ☆49Updated last year
- A centralized place for deep thinking code and experiments☆82Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- Code associated to papers on superposition (in ML interpretability)☆27Updated 2 years ago
- Image augmentation library for Jax☆39Updated last year
- 👑 Pytorch code for the Nero optimiser.☆20Updated 2 years ago
- Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks☆10Updated 10 months ago
- PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆36Updated 3 years ago
- ☆20Updated last year
- A metrics library for the JAX ecosystem☆40Updated 2 years ago
- ☆19Updated last year
- A JAX implementation of stochastic addition.☆14Updated 2 years ago
- JAX implementation of "Fine-Tuning Language Models with Just Forward Passes"☆19Updated last year
- ☆192Updated 2 weeks ago
- A case study of efficient training of large language models using commodity hardware.☆69Updated 2 years ago
- ☆60Updated 3 years ago
- A simple hypernetwork implementation in jax using haiku.☆23Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Code for minimum-entropy coupling.☆31Updated 9 months ago
- ☆24Updated 6 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆36Updated 2 years ago
- ☆26Updated 2 years ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆52Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆33Updated last year
- A collection of meta-learning algorithms in Jax☆23Updated 2 years ago
- The Energy Transformer block, in JAX☆57Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆173Updated this week