nsfzyzz / Generalization_metrics_for_NLP

Related projects: ⓘ

• aw31 / empirical-ntks
  Efficient empirical NTKs in PyTorch
  ☆15Updated 2 years ago
• YefanZhou / TempBalance
  [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
  ☆24Updated 9 months ago
• locuslab / edge-of-stability
  ☆56Updated 3 years ago
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆93Updated last month
• kwignb / NeuralTangentKernel-Papers
  Neural Tangent Kernel Papers
  ☆84Updated 6 months ago
• MadryLab / trak
  A fast, effective data attribution method for neural networks in PyTorch
  ☆170Updated this week
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆79Updated last year
• reds-lab / LAVA
  This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
  ☆40Updated 3 months 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
  ☆18Updated 2 years ago
• ppope / dimensions
  Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J
  ☆63Updated 5 months ago
• dtsip / in-context-learning
  ☆187Updated 4 months ago
• ssagawa / overparam_spur_corr
  An Investigation of Why Overparameterization Exacerbates Spurious Correlations
  ☆30Updated 4 years ago
• tml-epfl / sharpness-vs-generalization
  A modern look at the relationship between sharpness and generalization [ICML 2023]
  ☆42Updated last year
• tfjgeorge / nngeometry
  {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch
  ☆204Updated last month
• gortizji / linearized-networks
  Source code of "What can linearized neural networks actually say about generalization?
  ☆17Updated 2 years ago
• mueller-mp / SAM-ON
  ☆31Updated 7 months ago
• tml-epfl / understanding-sam
  Towards Understanding Sharpness-Aware Minimization [ICML 2022]
  ☆34Updated 2 years ago
• alstonlo / torch-influence
  A simple PyTorch implementation of influence functions.
  ☆75Updated 3 months ago
• thegregyang / NTK4A
  Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
  ☆93Updated 4 years ago
• deep-lab / DeepnetHessian
  Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)
  ☆17Updated 5 years ago
• locuslab / tofu
  Landing Page for TOFU
  ☆79Updated 3 months ago
• harshays / simplicitybiaspitfalls
  The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)
  ☆39Updated 7 months ago
• google-research / heldout-influence-estimation
  ☆61Updated 3 years ago
• KellerJordan / REPAIR
  Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
  ☆43Updated 7 months ago
• devansh20la / LPF-SGD
  ☆14Updated last year
• JeanKaddour / WASAM
  Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)
  ☆25Updated last year
• tding1 / Neural-Collapse
  [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features
  ☆50Updated 2 years ago
• JonasGeiping / fullbatchtraining
  Training vision models with full-batch gradient descent and regularization
  ☆37Updated last year
• ZaydH / influence_analysis_papers
  Influence Analysis and Estimation - Survey, Papers, and Taxonomy
  ☆58Updated 6 months ago
• themrzmaster / git-re-basin-pytorch
  Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch
  ☆69Updated last year