awslabs / aws-cv-unique-information
We define and estimate smooth unique information of samples with respect to classifier weights and predictions. We compute these quantities for linearized neural networks.
☆11Updated 3 years ago
Alternatives and similar repositories for aws-cv-unique-information:
Users that are interested in aws-cv-unique-information are comparing it to the libraries listed below
- Invariant-feature Subspace Recovery (ISR)☆23Updated 2 years ago
- ☆12Updated last year
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 3 years ago
- Distributional and Outlier Robust Optimization (ICML 2021)☆26Updated 3 years ago
- Coresets via Bilevel Optimization☆65Updated 4 years ago
- ☆48Updated 2 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 3 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 4 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆41Updated last year
- Predicting Out-of-Distribution Error with the Projection Norm☆17Updated 2 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- ☆36Updated 3 years ago
- ☆54Updated 4 years ago
- ☆30Updated 3 years ago
- ☆64Updated 4 years ago
- Code for PCA-OGD (AISTATS 2021)☆11Updated 3 years ago
- ☆20Updated 4 years ago
- ☆50Updated last year
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆34Updated last year
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆70Updated 9 months ago
- ☆31Updated 2 years ago
- Code repository for the paper "Invariant and Transportable Representations for Anti-Causal Domain Shifts"☆16Updated 2 years ago
- Energy-Based Models for Continual Learning Official Repository (PyTorch)☆40Updated 2 years ago
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆12Updated last year
- Gradient-based Hyperparameter Optimization Over Long Horizons☆13Updated 3 years ago
- This is the source code for Learning Deep Kernels for Non-Parametric Two-Sample Tests (ICML2020).☆48Updated 3 years ago