teddykoker / grokking

Related projects ⓘ

Alternatives and complementary repositories for grokking

• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆63Updated 2 years ago
• thegregyang / NNspectra
  Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube
  ☆47Updated 5 years ago
• google / spectral-density
  Hessian spectral density estimation in TF and Jax
  ☆115Updated 4 years ago
• thegregyang / NTK4A
  Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
  ☆97Updated 4 years ago
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆58Updated 3 years ago
• lixilinx / psgd_torch
  Pytorch implementation of preconditioned stochastic gradient descent (affine group preconditioner, low-rank approximation preconditioner …
  ☆127Updated last month
• bobby-he / Neural_Tangent_Kernel
  ☆67Updated 5 years ago
• f-t-s / CGD
  This repository contains the Julia code for the paper "Competitive Gradient Descent"
  ☆23Updated 4 years ago
• g-benton / hessian-eff-dim
  Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited
  ☆36Updated last year
• akbir / deq-jax
  [NeurIPS'19] Deep Equilibrium Models Jax Implementation
  ☆37Updated 4 years ago
• fwcore / mean-field-theory-deep-learning
  paper lists and information on mean-field theory of deep learning
  ☆75Updated 5 years ago
• HazyResearch / structured-nets
  Structured matrices for compressing neural networks
  ☆67Updated last year
• gehring / fax
  ☆78Updated 3 years ago
• james-simon / eigenlearning
  codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"
  ☆49Updated last year
• isl-org / LMRS
  Source code for ICLR 2020 paper: "Learning to Guide Random Search"
  ☆39Updated 2 months ago
• g-benton / loss-surface-simplexes
  ☆97Updated 2 years ago
• 4rtemi5 / imax
  Image augmentation library for Jax
  ☆37Updated 7 months ago
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆60Updated 2 years ago
• ganguli-lab / degrees-of-freedom
  ☆36Updated 2 years ago
• locuslab / monotone_op_net
  Monotone operator equilibrium networks
  ☆51Updated 4 years ago
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆49Updated last year
• ejmichaud / grokking-squared
  ☆22Updated last year
• kazukiosawa / ngd_in_wide_nn
  simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…
  ☆14Updated 4 years ago
• bremen79 / parameterfree
  Parameter-Free Optimizers for Pytorch
  ☆109Updated 6 months ago
• n2cholas / jax-resnet
  Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).
  ☆104Updated 2 years ago
• jambo6 / neuralRDEs
  Code for: "Neural Rough Differential Equations for Long Time Series", (ICML 2021)
  ☆115Updated 3 years ago
• choidami / sst
  ☆49Updated 4 years ago
• fsschneider / DeepOBS
  DeepOBS: A Deep Learning Optimizer Benchmark Suite
  ☆103Updated 11 months ago
• fKunstner / limitations-empirical-fisher
  Limitations of the Empirical Fisher Approximation
  ☆45Updated 4 years ago