awslabs / aws-cv-unique-informationLinks
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 4 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
Sorting:
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 4 years ago
- Invariant-feature Subspace Recovery (ISR)☆23Updated 2 years ago
- ☆22Updated last year
- Coresets via Bilevel Optimization☆66Updated 4 years ago
- ☆12Updated last year
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- Distributional and Outlier Robust Optimization (ICML 2021)☆27Updated 3 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆31Updated 4 years ago
- Predicting Out-of-Distribution Error with the Projection Norm☆19Updated 2 years ago
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 2 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆122Updated 3 years ago
- Official Code Repository for La-MAML: Look-Ahead Meta-Learning for Continual Learning"☆76Updated 4 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 4 years ago
- ☆14Updated 4 years ago
- ☆63Updated 4 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆24Updated 3 years ago
- ☆32Updated 2 years ago
- ☆26Updated 3 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- ☆107Updated last year
- ☆38Updated 7 months ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- Official code for ICLR 2020 paper "A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning."☆100Updated 4 years ago
- The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization".☆13Updated 3 years ago
- ☆20Updated 5 years ago
- ☆49Updated 2 years ago
- ☆13Updated 5 years ago
- This repository contains implementations of the paper, Bayesian Model-Agnostic Meta-Learning.☆60Updated 5 years ago
- This is the source code for Learning Deep Kernels for Non-Parametric Two-Sample Tests (ICML2020).☆49Updated 4 years ago
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 4 years ago