ppope / dimensions

Related projects ⓘ

Alternatives and complementary repositories for dimensions

• facebookresearch / BalancingGroups
  Simple data balancing baselines for worst-group-accuracy benchmarks.
  ☆40Updated last year
• MichaelArbel / GeneralizedEBM
  ☆53Updated 3 months ago
• tml-epfl / sharpness-vs-generalization
  A modern look at the relationship between sharpness and generalization [ICML 2023]
  ☆43Updated last year
• ansuini / IntrinsicDimDeep
  Code for the intrinsic dimensionality estimate of data representations
  ☆77Updated 4 years ago
• PolinaKirichenko / deep_feature_reweighting
  ☆105Updated last year
• ruiqigao / recovery_likelihood
  ☆49Updated 3 years ago
• avirmaux / lipEstimation
  ☆57Updated last year
• MadryLab / BREEDS-Benchmarks
  ☆55Updated 4 years ago
• tml-epfl / sgd-sparse-features
  SGD with large step sizes learns sparse features [ICML 2023]
  ☆32Updated last year
• point0bar1 / ebm-anatomy
  PyTorch implementation of Algorithm 1 of "On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models"
  ☆36Updated 3 months ago
• wgrathwohl / VERA
  ☆62Updated 9 months ago
• bobby-he / Neural_Tangent_Kernel
  ☆67Updated 5 years ago
• yaodongyu / Rethink-BiasVariance-Tradeoff
  Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
  ☆49Updated 3 years ago
• tml-epfl / understanding-sam
  Towards Understanding Sharpness-Aware Minimization [ICML 2022]
  ☆35Updated 2 years ago
• gortizji / linearized-networks
  Source code of "What can linearized neural networks actually say about generalization?
  ☆18Updated 3 years ago
• ssagawa / overparam_spur_corr
  An Investigation of Why Overparameterization Exacerbates Spurious Correlations
  ☆30Updated 4 years ago
• cemanil / LNets
  Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).
  ☆55Updated 4 years ago
• thegregyang / NTK4A
  Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
  ☆97Updated 4 years ago
• AlexanderMath / fasth
  Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.
  ☆69Updated 3 months ago
• JonasGeiping / fullbatchtraining
  Training vision models with full-batch gradient descent and regularization
  ☆38Updated last year
• bneyshabur / generalization-bounds
  Computing various measures and generalization bounds on convolutional and fully connected networks
  ☆35Updated 5 years ago
• cunningham-lab / igr
  ☆31Updated 4 years ago
• wronnyhuang / gen-viz
  Code for the paper "Understanding Generalization through Visualizations"
  ☆60Updated 3 years ago
• MadryLab / failure-directions
  Distilling Model Failures as Directions in Latent Space
  ☆45Updated last year
• aniruddhraghu / meta-pretraining
  Code accompanying paper: Meta-Learning to Improve Pre-Training
  ☆37Updated 3 years ago
• js-d / sim_metric
  ☆35Updated last year
• yilundu / ebm_compositionality
  [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models
  ☆43Updated last year
• harshays / simplicitybiaspitfalls
  The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)
  ☆39Updated 10 months ago
• Faruk-Ahmed / predictive_group_invariance
  ☆34Updated 3 years ago