Alternatives and similar repositories for SAM-overparam

Users that are interested in SAM-overparam are comparing it to the libraries listed below

• edong6768 / Malet
  🔨 Malet (Machine Learning Experiment Tool) is a tool for efficient machine learning experiment execution, logging, analysis, and plot ma…
  ☆17Updated 6 months ago
• LOG-postech / Sassha
  [ICML 2025] Official Pytorch code for "SASSHA: Sharpness-aware Adaptive Second-order Optimization With Stable Hessian Approximation"
  ☆19Updated 2 months ago
• LOG-postech / ZIP
  ☆17Updated 7 months ago
• ssbin4 / Closer-Intervention-CBM
  ☆25Updated last year
• deep-lab / DeepnetHessian
  Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)
  ☆16Updated 6 years ago
• tml-epfl / sam-low-rank-features
  Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]
  ☆28Updated 2 years ago
• tml-epfl / understanding-sam
  Towards Understanding Sharpness-Aware Minimization [ICML 2022]
  ☆35Updated 3 years ago
• mueller-mp / SAM-ON
  ☆34Updated last year
• locuslab / edge-of-stability
  ☆71Updated 10 months ago
• hushon / JAX-ResNet-CIFAR10
  Simple CIFAR10 ResNet example with JAX.
  ☆23Updated 4 years ago
• LOG-postech / rethinking-LLM-pruning
  ☆28Updated 8 months ago
• tml-epfl / sharpness-vs-generalization
  A modern look at the relationship between sharpness and generalization [ICML 2023]
  ☆43Updated 2 years ago
• ksachdeva / tiny-imagenet-tfds
  tiny-imagenet dataset downloader & reader using tensorflow_datasets (tfds) api
  ☆20Updated 6 years ago
• yoonholee / DivDis
  ☆39Updated 3 years ago
• hoonyyhoon / Synflow_SNIP_GraSP
  Comparison of method "Pruning at initialization prior to training" (Synflow/SNIP/GraSP) in PyTorch
  ☆17Updated last year
• harshays / simplicitybiaspitfalls
  The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)
  ☆41Updated last year
• fKunstner / noise-sgd-adam-sign
  ☆17Updated 2 years ago
• omihub777 / MLP-Mixer-CIFAR
  PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from s…
  ☆36Updated 3 years ago
• mil-ad / prospr
  Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients
  ☆32Updated 3 years ago
• IST-DASLab / WoodFisher
  Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)
  ☆53Updated 4 years ago
• gortizji / linearized-networks
  Source code of "What can linearized neural networks actually say about generalization?
  ☆20Updated 4 years ago
• devansh20la / LPF-SGD
  ☆17Updated 2 years ago
• tfjgeorge / nngeometry
  {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch
  ☆215Updated last month
• jaeho-lee / oce
  Codes for "Learning bounds for risk-sensitive learning," NeurIPS 2020 (or see arXiv 2006.08138)
  ☆11Updated 5 years ago
• JonasGeiping / fullbatchtraining
  Training vision models with full-batch gradient descent and regularization
  ☆39Updated 2 years ago
• nsfzyzz / loss_landscape_taxonomy
  [NeurIPS 2021] code for "Taxonomizing local versus global structure in neural network loss landscapes" https://arxiv.org/abs/2107.11228
  ☆19Updated 3 years ago
• JWoong148 / ContinualTrajectoryShifting
  Pytorch implementation of "Large-Scale Meta-Learning with Continual Trajectory Shifting" (ICML 2021)
  ☆17Updated 4 years ago
• AngusDujw / SAF
  ☆36Updated 2 years ago
• cybertronai / autograd-hacks
  ☆157Updated 3 years ago
• verbiiyo / rigl-torch
  Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.
  ☆60Updated 3 years ago