tml-epfl / why-weight-decay

Related projects ⓘ

Alternatives and complementary repositories for why-weight-decay

• zyushun / hessian-spectrum
  Code for the paper: Why Transformers Need Adam: A Hessian Perspective
  ☆40Updated 6 months ago
• srush / mamba-scans
  Blog post
  ☆16Updated 8 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆23Updated 4 months ago
• RobertCsordas / linear_layer_as_attention
  The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …
  ☆16Updated 11 months ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆48Updated 2 months ago
• f-dangel / singd
  [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
  ☆19Updated this week
• radarFudan / Curse-of-memory
  Curse-of-memory phenomenon of RNNs in sequence modelling
  ☆19Updated this week
• ermongroup / fast_feedforward_computation
  Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021
  ☆26Updated 3 years ago
• fKunstner / noise-sgd-adam-sign
  ☆15Updated last year
• gregorbachmann / scaling_mlps
  ☆50Updated 4 months ago
• thjashin / multires-conv
  Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)
  ☆120Updated last year
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• facebookresearch / ViP-MAE
  This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision
  ☆37Updated last year
• epfml / schedules-and-scaling
  ☆50Updated last week
• radarFudan / mamba-minimal-jax
  ☆29Updated last month
• stanislavfort / dissect-git-re-basin
  Replicating and dissecting the git-re-basin project in one-click-replication Colabs
  ☆36Updated 2 years ago
• apple / ml-agm
  ☆42Updated 6 months ago
• sustcsonglin / mamba-triton
  ☆45Updated 9 months ago
• wjxts / RegularizedBN
  ☆21Updated last year
• sjelassi / transformers_ssm_copy
  ☆24Updated 8 months ago
• formll / resolving-scaling-law-discrepancies
  ☆15Updated 4 months ago
• berlino / seq_icl
  ☆50Updated 5 months ago
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆79Updated last year
• OpenNLPLab / HGRN
  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…
  ☆61Updated 6 months ago
• rtaori / data_feedback
  Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"
  ☆15Updated 2 years ago
• NingMiao / InstaAug
  ☆13Updated last year
• locuslab / T-MARS
  Code for T-MARS data filtering
  ☆35Updated last year
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆89Updated 2 months ago
• epfml / REQ
  ☆16Updated 4 months ago
• Doraemonzzz / hgru2-pytorch
  ☆21Updated last month